Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

795results about How to "Improve concealment" patented technology

Enterprise network security test and evaluation method and system

The invention relates to the field of network security testing, in particular to an enterprise network security testing and evaluating method and system. The method comprises the following steps: carrying out system access network equipment detection on an enterprise network system, carrying out topology interaction connection, and constructing a network equipment topology structure diagram; setting configuration feature mapping is carried out on the network equipment topological structure diagram, panoramic virtual modeling is carried out, and an enterprise IT panoramic virtual environment is constructed; obtaining a historical log of an enterprise network system; carrying out enterprise business application behavior analysis on the historical log of the enterprise network system, and carrying out intrusion attack simulation to obtain an intrusion attack behavior simulation sample; and performing camouflage carrier packaging processing on the intrusion attack behavior simulation sample, performing coverage type intrusion simulation on the enterprise IT panoramic virtual environment to obtain an intrusion simulation virtual environment, and collecting virtual environment intrusion simulation response data. According to the invention, efficient and accurate enterprise network security assessment is realized.
Owner:SHENZHEN JIANAN RUNXING SAFETY TECH CO LTD

Microgrid intelligent safety secondary voltage control method based on reinforcement learning

The invention relates to a micro-grid intelligent safety secondary voltage control method based on reinforcement learning, and belongs to the technical field of power grids. The method comprises the following steps: firstly, establishing a micro-grid secondary control model under hybrid network attack; a DoS attack defense network based on deep learning is designed, a self-adaptive FDI attack compensation state observer is designed, compensation for unknown FDI attacks is established, a self-adaptive law of compensation signals is designed, and estimation of the system state under network attacks is achieved. An evaluation-execution structure is constructed based on reinforcement learning, a virtual optimal controller and an actual optimal controller are designed in combination with a backstepping method, unknown parts in a system model, an evaluation network and an execution network are approximated by using a neural network, and a weight adjustment law is given. And introducing a log type barrier function into the performance index function, and constraining the output in a fixed constant interval to meet the constraint condition. The method can cope with DoS attacks and FDI attacks, and ensures stable control and safe operation of the secondary voltage of the micro-grid.
Owner:CHONGQING UNIV

Automobile information safety fuzzy test method and system based on large model

The invention belongs to the technical field of automobile information safety fuzzy testing, discloses an automobile information safety fuzzy testing method based on a large model, and develops optimization application research of LLMs in an automobile software fuzzy testing scene by utilizing the advantages of an artificial intelligence technology in the aspects of data processing, natural language interaction, generalization ability and the like. The concealment and effectiveness of the test set generated by the fuzz test are optimized, and the fuzz test process efficiency is improved. Through the implementation of the invention, related key technologies are applied to the fuzz test of the automobile, and other related products and enterprises in China are radiated by writing technical standards, so that the fuzz test system can be used as an application demonstration and sample plate of the fuzz test of the intelligent driving automobile. According to market analysis, fuzzy test calculation is carried out on 100 thousand automobiles every year according to the method, and the data safety and the system safety are improved.
Owner:BEIJING INST OF TECH

Communication encryption method based on two-dimensional inorganic / inorganic Van der Waals heterojunction polarized photoelectric detector

The invention discloses a communication encryption method based on a two-dimensional inorganic / inorganic Van der Waals heterojunction polarized photoelectric detector, and belongs to the technical field of photoelectric devices. The photoelectric detector comprises a substrate, two-dimensional MoSe2 material layers, two-dimensional ReS2 material layers and a thin film electrode, wherein the two two-dimensional material layers form a Van der Waals vertical heterojunction and are of an II-type heterostructure; due to anisotropic light absorption of ReS2, effective carrier collection and transport capabilities of MoSe2 and an inhibition effect of heterojunction on dark current, the photoelectric property of the two-dimensional ReS2 / MoSe2 photoelectric detector is obviously improved, and meanwhile, the two-dimensional ReS2 / MoSe2 photoelectric detector has high responsivity of 89.4 A / W, fast response speed of 30.5 s and polarization sensitive characteristics, and can be applied to the field of photoelectric detectors. On the basis, information is subjected to multiple encryption by means of a polarization state information encryption technology, so that the concealment and security of an information transmission process can be greatly improved, and a new possibility is provided for the development of a security communication technology in the future.
Owner:NANJING UNIV OF POSTS & TELECOMM

File transmission protection method, system and equipment based on multiple encryption algorithms

The invention discloses a file transmission protection method, system and device based on multiple encryption algorithms, and relates to the technical field of information, and the method comprises the steps: selecting a target file needing to be transmitted, carrying out the preprocessing, and generating file fragments; analyzing the sensitivity of each file fragment, and performing hierarchical encryption processing to obtain an encrypted fragment set; selecting a steganography carrier file, and embedding the encrypted fragments into the carrier file to generate a steganography index table; generating a dynamic session key based on the confusion key pool, encrypting the steganographic file transmission layer and embedding a dynamic key generation parameter; the receiving end generates a session key according to the transmission message header, decrypts the transmission layer data, extracts the steganographic file and decrypts the steganographic file; recombining the decrypted and recovered fragmented data into a complete file according to an identifier sequence; by dynamically matching the steganography carrier file, the efficient embedding of the fragmented data and the generation of the steganography index table are realized, and the concealment and the adaptability in the transmission process are ensured.
Owner:SUZHOU OMEGA NETWORK TECH CO LTD

Safety protection method and device for intelligent networked automobile

The invention provides a safety protection method and device for an intelligent networked automobile, and the method comprises the steps: detecting a vehicle control abnormal instruction in a communication process between a target vehicle and a cloud end based on a vehicle control behavior characterization model and an abnormal behavior classification learning model; and based on the malicious traffic identification model, identifying hidden malignant traffic in the process of communication between the target vehicle and the cloud, through a deep reinforcement learning confrontation defense mode, a decision control model is trained according to a vehicle control abnormal instruction and hidden malignant flow, and the decision control model is used for carrying out safety protection on the intelligent network connection vehicle. Therefore, high-precision and high-reliability detection of attacks such as vehicle control instruction tampering attacks and strongly hidden malicious traffic under the intelligent network connection vehicle-cloud cooperation scene is realized, the attack concealment and attack efficiency are effectively improved, the robustness and generalization of the model are enhanced, and the method is suitable for the intelligent network connection vehicle-cloud cooperation scene. And the communication safety, the data safety and the driving safety of the intelligent networked automobile ecological system are improved.
Owner:WUHAN HONGXU INFORMATION TECH

Cross-modal steganography method and device, equipment and storage medium

The invention provides a cross-modal steganography method and device, equipment and a storage medium, and the method comprises the steps: inputting a carrier image and a ciphertext image corresponding to ciphertext text data into a preset encoder, enabling a learnable wavelet transform network and a reversible neural network in the encoder to carry out the forward feature extraction of the carrier image and the ciphertext image, and obtaining a feature extraction result; obtaining a target carrier feature vector corresponding to the carrier image and a target ciphertext feature vector corresponding to the ciphertext image; and generating ciphertext cross-modal steganography result data corresponding to the ciphertext text data based on the target carrier feature vector and the target ciphertext feature vector for network transmission. According to the method and the device, the ciphertext text data of the text mode can be embedded into the carrier image of the image mode, a multi-mode steganography technology is realized, the steganography concealment and robustness of the ciphertext can be effectively improved, and the ciphertext network transmission security and reliability can be further improved.
Owner:BEIJING UNIV OF POSTS & TELECOMM +1

Vibration monitoring and noise real-time forecasting method based on ship three-dimensional acoustic elasticity theory

A vibration monitoring and noise real-time forecasting method based on the ship three-dimensional acoustic elasticity theory comprises a vibration online monitoring and noise real-time forecasting device based on the ship three-dimensional acoustic elasticity theory, the specific structure is that the vibration online monitoring and noise real-time forecasting device comprises a multi-channel collector, the multi-channel collector is connected with a POE switch through a network cable, the POE switch is connected with a reinforcing all-in-one machine through a network cable, and the reinforcing all-in-one machine is connected with the ship three-dimensional acoustic elasticity theory. Vibration online monitoring and noise real-time forecasting software based on the ship three-dimensional acoustic elasticity theory is installed on the reinforced all-in-one machine; the acceleration sensor is installed at the position of a vibration monitoring point and is connected with the multi-channel collector. A vibration on-line monitoring technology and a ship underwater radiation noise forecasting method are combined, and ship vibration on-line monitoring and underwater radiation noise real-time forecasting are achieved.
Owner:CHINA SHIP SCIENTIFIC RESEARCH CENTER

Pixel point guided black box attack method and device

The invention discloses a pixel-point-guided black box attack method and device, and relates to the field of unmanned aerial vehicle countering. The method and the device are used for solving the problems that the current confrontation sample generation method under the black box attack depends too much on a model and lacks key semantic positioning, redundant disturbance and unnecessary pixel tampering are easily caused, the query frequency is high, and the attack success rate is low. Comprising the following steps: determining key pixel points in a clean sample and a mask matrix corresponding to the key pixel points according to an adaptive particle swarm optimization (APSO) algorithm; according to the difference between the clean sample identification tag and the target image identification tag, key parameters generated by controlling the target image to resist disturbance are obtained through a PID controller, and a tampered confrontation sample and a first identification tag of the tampered confrontation sample are obtained according to the key parameters and the mask matrix; and according to the difference between the tampered confrontation sample first identification tag and the target image identification tag, obtaining a confrontation attack optimization model and an optimal confrontation attack sample.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Watermarking method based on mutual information screening and IGWO optimization

The invention relates to a watermarking method based on mutual information screening and IGWO optimization, and the method comprises the following steps: 1, carrying out the attribute screening through a mutual information method, obtaining an attribute set which is highly related to the classification accuracy, determining an unimportant attribute set, and forming a complete attribute set after the mutual information screening; step 2, based on the attribute set screened by the mutual information attributes in the step 1, carrying out watermark embedding operation for an unimportant attribute set to obtain a watermark data set containing a watermark; and step 3, based on the watermark data set generated in the step 2, watermark data are classified through a decision tree model, and the watermark embedding strength and position are optimized by applying an IGWO algorithm. The method can effectively solve the problem of traceability responsibility of matched power grid service data.
Owner:STATE GRID TIANJIN ELECTRIC POWER COMPANY +1

Data encryption method and system for solid state disk

The invention relates to the field of solid state disk data encryption, in particular to a solid state disk data encryption method and system. The method comprises the following steps: performing partition table structure analysis on the solid state disk, and performing hard disk capacity distribution analysis to obtain hard disk capacity distribution data; acquiring to-be-written hard disk data; performing data partitioning processing on to-be-written hard disk data, and performing confusion encryption processing so as to construct a confusion encrypted data sequence; obtaining a pre-stored random picture; pixel channel decomposition is carried out on a pre-stored random picture one by one, and maximum data steganography distribution density calculation is carried out, so that the maximum data steganography distribution density is obtained; and based on the maximum data steganography distribution density, carrying out data distribution encryption steganography on a pre-stored random picture by using the confused encrypted data sequence, and carrying out visual deviation fine tuning so as to generate a visual fine tuning steganography picture. According to the invention, efficient and safe solid state disk data encryption is realized.
Owner:SHENZHEN WEIKEWEIYE ELECTRONIC TECH CO LTD

User local data distribution reasoning attack method based on federal learning

The invention relates to the technical field of machine learning, in particular to a user local data distribution reasoning attack method based on federal learning. The method comprises the steps of generating an auxiliary data set, constructing a simulated attack user data set, training a shadow model, training a user model, calculating cosine similarity, adjusting the data proportion of various labels in the simulated attack user data set, forming an updated federal learning global model, judging a training termination condition, and obtaining a training result. Obtaining local data distribution of the target attack user; according to the method, the data privacy security problem caused by federal learning distributed training characteristics is solved; by deploying an auxiliary data set and a shadow model at a server side, analyzing and simulating an attack user data set by using a gradient direction, the distribution of local data of a target attack user on each category is dynamically deduced, the label distribution of the target attack user is revealed, and meanwhile, the method has relatively high concealment, adaptability and effectiveness.
Owner:SONGSHAN LABORATORY +1

Inter-satellite link secure transmission method based on hybrid covert strategy

The invention discloses an inter-satellite link secure transmission method based on a hybrid covert strategy, and belongs to the field of electronic communication. According to the invention, more randomness and friendly interference are introduced from three layers of a network layer, an MAC layer and a physical layer, and potential eavesdroppers are confused; in a network layer, a random routing unit is adopted, a plurality of routing paths meeting communication requirements are dynamically selected to replace a single optimal path, and a selection probability is distributed to each routing path according to routing metrics. In the MAC layer, the spectrum sharing technology is utilized to distribute less power for the information needing to be hidden, so that the signal detection probability is reduced, and the communication security is improved. In a physical layer, a rate division multiple access unit and a superposition coding technology are adopted, so that a plurality of users can efficiently share the same time-frequency resource at the same time. According to the invention, the communication efficiency can be improved, and the transmission randomness and complexity can be further improved, so that the communication security is enhanced.
Owner:BEIJING INST OF TECH

Water-air cross-medium bionic robot

The invention belongs to the field of underwater bionic robots, and relates to a water-air cross-medium bionic robot which comprises a shell, a reciprocating swing mechanism, a wing module, a pelvic fin module and a control system, the shell comprises a front-end shell and a rear-end tail, the front-end shell is connected with the rear-end tail through the reciprocating swing mechanism, and the front-end shell is connected with the rear-end tail through the reciprocating swing mechanism. The wing module is installed at the top of the upper portion of the front-end shell, the pelvic fin module is installed on the rear side of the lower portion of the front-end shell, and the control system is installed in the front-end shell and connected with the reciprocating swing mechanism through a signal line to control the reciprocating swing mechanism to rotate so as to drive the tail of the rear end to swing to conduct cruise propelling and control the pelvic fin module to rotate to dive upwards and float downwards. The wing modules are controlled to be opened and closed to achieve water breaking gliding. The robot is compact in structure, small in size and light in weight, can achieve various motion postures in air and water, can meet application scenes in various environments, and particularly has high adaptability in the aspects of water-air cross-medium information collection and sending, information exploration and the like.
Owner:HAINAN UNIV

Vehicle-mounted multi-type electromagnetic ejection device and control method thereof

The invention discloses a vehicle-mounted multi-type electromagnetic ejection device and a control method thereof, and relates to the technical field of vehicle-mounted unmanned aerial vehicles, the vehicle-mounted multi-type electromagnetic ejection device comprises a vehicle head and a compartment, an energy storage unit is arranged at the bottom of one end of the compartment, and a charger is arranged at the top of the energy storage unit; a driving system is arranged on one side of the energy storage unit, a control unit is arranged in the driving system, and a switching unit is arranged on one side of the driving system; a hangar is arranged at the other end of the compartment, and an adjustable electromagnetic ejection unit is arranged on one side of the hangar. According to the vehicle-mounted multi-type electromagnetic catapult, only one set of power supply equipment and one set of driving system need to be adopted, catapulting tasks of unmanned aerial vehicles of various types can be adapted at the same time, high-frequency continuous launching of the unmanned aerial vehicles of different types is achieved, the adaptive capacity of the vehicle-mounted multi-type electromagnetic catapulting device is wider, and the launching flexibility and efficiency of the multi-type unmanned aerial vehicles are improved; compared with multiple sets of electromagnetic launching units launched by a single unmanned aerial vehicle, the continuous launching capability of multiple types of unmanned aerial vehicles is improved, and the manufacturing and maintenance cost of the device is saved.
Owner:HUNAN YINHE ATITAN TECH CO LTD

Positioning device

The utility model provides a positioning device. The positioning device comprises a shell, a shading block and a circuit module arranged in the shell, the circuit module comprises a first circuit board, a communication module, a positioning module, a control module and a light sensor, and the communication module, the positioning module and the light sensor are all in electric signal connection with the control module; the shell is provided with an installation face used for being attached to equipment to be positioned, a light through hole is formed in the shell wall, close to one side of the installation face, of the shell, the light sensor corresponds to the light through hole, and the light shading block is movably arranged in the light through hole to block the light through hole; when the shell is detached from the to-be-positioned equipment, the shading block is separated from the light through hole, the light sensor receives external light through the light through hole, converts a light signal into an electric signal and transmits the electric signal to the control module, and the control module controls the communication module to send alarm information to a mobile terminal of a preset emergency contact person. The positioning device provided by the utility model has a dismounting alarm function, so that the safety is improved.
Owner:SHENZHEN CHEZHIJIE INTERNET OF VEHICLES CO LTD

Intelligent covert communication method and device based on artificial interference and 3D beamforming

The invention discloses an intelligent covert communication method and device based on artificial interference and 3D beamforming, and the method specifically comprises the steps: firstly building a multi-antenna covert communication system model based on channel state information and antenna gain network parameters; then, based on a radio frequency signal receiving principle, establishing a signal detection model of the monitoring machine, calculating an omission ratio and a false alarm rate of the monitoring machine, obtaining a minimum error detection probability of the monitoring machine, and establishing an optimization problem of hiding rate maximization; constructing a depth determination strategy gradient (DDPG) neural network; and finally, on the basis of the DDPG neural network, an intelligent covert communication algorithm based on artificial interference and 3D beam forming is adopted, and the covert rate of the covert communication system is optimized. According to the method, the transmission rate of the legal receiver can be maximized under the condition of meeting the concealment limitation, the communication performance and the concealment performance are enhanced, and the intelligent concealed communication requirements in various scenes can be met.
Owner:SYST OVERALL RES INST INST OF SYST ENG ACAD OF MILITARY SCI

Hidden animal real-time monitoring equipment

The utility model discloses real-time animal monitoring equipment with concealment, and relates to the technical field of monitoring equipment, the real-time animal monitoring equipment comprises a mounting assembly, a monitor and a mimicry concealing assembly, the mounting assembly comprises a first fastening ring and a second fastening ring, one side of the first fastening ring is provided with the second fastening ring, and the second fastening ring is provided with the monitor. A rotating motor is fixed to the outer side of the first fastening ring, an electric telescopic rod is installed on one side of an output shaft of the rotating motor, a servo motor is fixed to the top end of the electric telescopic rod, a monitor is installed on the upper side of a rotating shaft of the servo motor, and mimicry hiding assemblies are installed on the outer sides of the upper portion and the lower portion of the monitor. According to the real-time animal monitoring equipment with the concealment performance, the outer surfaces of the electric telescopic rod, the protective cover and the upper cover frame are all provided with the branch-imitated camouflage coatings, and meanwhile, the outer side of the upper cover frame is fixedly provided with the imitated branches, so that the whole equipment installed on a trunk can simulate the branches, the concealment performance is good, and the possibility that the equipment is damaged by animals is reduced.
Owner:SHENZHEN ZHONGTIAN ENVIRONMENT CO LTD

Adaptive amplitude modulation screening digital watermark optimization method and system

The invention discloses an optimization method and system of a self-adaptive amplitude modulation screening digital watermarking, and the method comprises the steps: converting an input RGB image into a CMYK image suitable for printing, and splitting four color channels of cyan, magenta, yellow and black of the CMYK image; calculating mutual influence among the channels after splitting, setting loss constants of the channels, and calculating fitness; searching a watermark region color block meeting the requirement on the carrier image, and splitting the searched watermark region color block according to an edge algorithm to obtain a channel and a region suitable for embedding a watermark; marking a color block containing a watermark to obtain a carrier image added with a mask; amplitude modulation screening operation is carried out on the carrier image, watermarks are embedded in channels and areas suitable for watermark embedding, and a final halftone target image is generated; the system comprises a color space conversion module, a fitness statistics module, a watermark area selection module, a mask processing module and a watermark embedding and amplitude modulation screening module. The system has the advantages of being good in image quality, flexible in printing resolution, high in watermark imperceptibility and the like.
Owner:XIDIAN UNIV

Watermark processing method and device for digital audio, equipment and storage medium

The invention discloses a digital audio watermark processing method and device, equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: receiving a watermark adding instruction, and carrying out Fourier transform on original host voice to obtain an audio signal; identifying a watermark information adding bit in the audio signal through the audio watermark model, and embedding a watermark message in the watermark information adding bit; the interfering audio signal and the audio signal carrying the watermark message are combined. Receiving the message extraction signal, and separating an interference audio signal in the combined audio signal; a watermark information adding bit in the audio signal is identified, and a watermark message is extracted from the watermark information adding bit. The invention also relates to the technical field of block chains, and the host voice is stored on a block chain network. According to the method, the watermark information adding position is automatically identified through the audio watermark model, so that the watermark information is added and extracted, the dependence on expert knowledge is remarkably reduced, and the watermark processing speed and efficiency are improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Audio watermark embedding method and device, electronic equipment and storage medium

The embodiment of the invention provides an audio watermark embedding method and device, electronic equipment and a storage medium, and belongs to the technical field of voice processing. The method comprises the following steps: carrying out attribute division on watermark attribute data to obtain watermark attribute blocks, and carrying out content division on watermark content data to obtain watermark content blocks; encoding the watermark attribute block, and combining the encoded attribute encoding sequence block and the watermark content block to obtain a target watermark data block; and embedding the target watermark data block into the target spectrum according to the coding rate to obtain a target audio. According to the embodiment of the invention, the watermark attribute block is coded, so that the watermark can be identified when the position of the watermark in the audio signal deviates; according to the audio watermark embedding method and device, the target watermark data block is embedded into the target frequency spectrum according to the coding rate, the audio watermark can be repeatedly embedded into the audio, when part of the audio watermark is damaged or lost, complete watermark information can still be extracted from the rest of the audio, and the audio watermark embedding effect is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Black box confrontation sample generation method for speech recognition system

InactiveCN119132286AImprove migration abilityAttack success rate guaranteedSpeech recognitionEngineeringGradient estimation
The invention discloses a black box confrontation sample generation method for a speech recognition system. The method comprises the following steps: inputting an original speech sample and a target text into an integrated attack output initial momentum and an initial confrontation sample; finite difference gradient estimation is carried out every fixed times, a current dominant frame in a voice confrontation sample is determined firstly, then the initial probability of selection of each sampling value is given, the final probability of selection of each sampling value is calculated according to the probability of selection of the dominant frame, and then finite difference gradient estimation is carried out; obtaining a gradient estimation value to update the probability that the sampling value is selected; for other iterations, selecting part of frames in the voice confrontation sample according to the probability that the dominant frame is selected, and adding a disturbance value to the selected frame to form a disturbed voice confrontation sample; the method has the advantages that on the premise that the voice content is not seriously damaged, it can be guaranteed that the voice is recognized as the pre-designed malicious content, and the mobility, the concealment, the query efficiency and the attack success rate of resisting the sample attack are greatly improved.
Owner:NINGBO UNIV

A method for pod system error calibration without knowing the ground position

The present invention proposes a pod system error calibration method without the need for a known ground position. It belongs to the technical field of optoelectronic pod error calibration. The method includes step one, pod installation and timing alignment, step two, starting image tracking for any target, step three, obtaining multiple sets of spatial pointing angle errors, and step four, calculating the attitude angle compensation value. The method solves the limitation of previous methods that some means are needed to extract and obtain the precise geographical location of the ground target point, and at the same time, it does not require the participation of complex detour routes and laser ranging, which greatly improves the convenience, timeliness and concealment of pod error calibration during flight, and provides support for subsequent high-precision target positioning and geographic guidance and tracking functions during the current flight. It not only greatly reduces the difficulty of calibration and the complexity of the process, but also brings great convenience to practical applications.
Owner:CHANGCHUN TONGSHI PHOTOELECTRIC TECH CO LTD

Relay satellite position optimization method and system based on satellite covert communication

The invention discloses a relay satellite position optimization method and system based on satellite covert communication, and the method comprises the following steps: (1) constructing a covert communication model in a satellite covert communication system, the covert communication model comprises a relay satellite, a transmitting base station which is located on the ground and transmits signals to the relay satellite, a receiving base station which is located on the ground and receives the signals through the relay satellite and transmits interference signals to interfere with the detection satellite, and a monitoring satellite which monitors the signals of the relay satellite and transmits interference signals to interfere with the receiving base station. (2) constructing a minimum total error detection probability calculation model of a monitoring satellite in the satellite covert communication system; (3) establishing a relay satellite position optimization model which takes the maximum covert communication rate as a target and takes the condition that the minimum total error detection probability of the monitoring satellite is greater than or equal to a preset threshold value as a constraint condition; and (4) solving the relay satellite position optimization model to obtain the optimal position of the relay satellite. According to the invention, the concealment and the communication rate can be improved.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Deep voice digital watermark streaming embedding and detecting method for privacy protection

The invention discloses a deep voice digital watermark streaming embedding and detection method for privacy protection, which effectively isolates user sensitive information and watermark information in voice content based on an end-cloud cooperative processing environment, and simultaneously realizes the beneficial effects of streaming embedding, interval labeling, watermarking counterfeiting prevention, channel robustness and the like. According to the technical scheme, scenes such as voice content copyright declaration and forged sample identification are supported, third-party watermark embedding and detection application is served, and in the whole watermark embedding stage, a server side generates universal watermark data only according to watermark information, so that the leakage risk of user privacy information is avoided. In a detection link, a receiving end user side adopts a third deep neural network to perform desensitization processing on audio content, so that a server side can only deduce existence of watermarks through processed desensitization data, direct contact between original voice data of a user and the server side is isolated, the user privacy protection level is remarkably improved, and the user experience is improved. And the sense of trust between the user and the third-party detection platform is improved.
Owner:ZHEJIANG UNIV

Method and device for processing right identification of cultural relic three-dimensional model

The invention discloses a method and a device for processing right identification of a cultural relic three-dimensional model, and the method comprises the steps: dividing the cultural relic three-dimensional model into at least one region based on the geometric features of the to-be-processed cultural relic three-dimensional model; determining a sensitivity parameter corresponding to each region based on the region feature corresponding to each region; based on the sensitivity parameter corresponding to each area, determining a processing parameter corresponding to each area, and processing the original right confirmation identification information corresponding to the area by using the processing parameter to obtain a target right confirmation identification; and adding the target right confirmation identifier to the cultural relic three-dimensional model to obtain a target cultural relic three-dimensional model. The corresponding processing parameters are determined according to the sensitive parameters of the cultural relic three-dimensional model area, it is ensured that the embedded identification information is difficult to perceive visually, the concealment and safety of the right confirmation identification information are improved, and copyright protection of the cultural relic three-dimensional model in public use is ensured.
Owner:HUNAN MANGO DIGITAL INTELLIGENCE ART TECH CO LTD

Bionic flexible flapping wing underwater robot

The invention discloses a bionic flexible flapping wing underwater robot which comprises a shell, two side wing flapping mechanisms located on the two sides of the shell, an empennage flapping mechanism located at the tail of the shell, a camera cabin located at the front end of the shell, a steering engine control cabin located at the front end of the interior of the shell and a gravity adjusting cabin located at the rear end of the interior of the shell. The side wing flapping mechanism comprises a side wing steering engine, a flapping assembly and a flexible side wing fin surface, the flapping assembly comprises a flapping transmission assembly, a fixing rod and a plurality of fin rays, one end of each fin ray is connected with the flapping transmission assembly, the middle of each fin ray is penetrated by the fixing rod, the other end of each fin ray is connected with the side wing fin surface, and the side wing steering engine is connected with and drives the flapping transmission assembly to drive one end of each fin ray to swing; all the fin rays are not in the same plane, and when the fin rays swing, the fin surfaces of the side wings swing in a wave shape. The device simulates the structural form, the motion characteristic and the driving mechanism of the natural aquatic organism manta ray, and has the characteristics of low noise, high maneuverability, small size, portability and high concealment.
Owner:XIANGTAN UNIV

Archimedes type ocean energy collecting device and hydrological monitoring station

The invention relates to the field of new energy power generation, in particular to an Archimedes type ocean energy collecting device and a hydrological monitoring station. The device comprises a floating body and a set of thin plate contact separation type TENG. The floating body is installed below a water body and can move up and down along with fluctuation, and then the thin plate loaded in the floating body is driven to make contact with the separation type TENG to generate power. The floating body comprises a silo, a floating barrel and an elastic annular waterproof belt connecting the silo and the floating barrel. The silo is upwards inserted into the buoy, and the waterproof belt is connected with the buoy and the silo to form a closed columnar cavity. The thin plate contact separation type TENG is installed in the columnar cavity and comprises a fixing mechanism, a connecting rod, a plurality of circular friction discs and a plurality of electrode discs. The friction discs and the electrode discs are alternately arranged in parallel in the axial direction of the columnar cavity. The friction disc and the electrode disc are respectively fixed on the buoy and the silo; the problem that an existing friction nanometer generator is not suitable for application scenes such as deep water is solved.
Owner:GUANGZHOU INSTITUTE OF BLUE ENERGY

In-vivo effusion drainage equipment for breast surgery

The invention relates to the technical field of medical drainage equipment, in particular to in-vivo effusion drainage equipment for breast surgery, which comprises a storage rack, a pair of drainage tubes and an overclothes for a patient to wear, two drainage bottles are placed in the storage rack, a box body is arranged at the top of the storage rack, and a driving mechanism is arranged in the middle of the interior of the box body; two first gas distribution mechanisms and two second gas distribution mechanisms are arranged in the box body and are symmetrically arranged relative to the driving mechanism. The first air distribution mechanism is driven by the driving mechanism to work to inflate and deflate the pressing air bag set, automatic pressing can be conducted on the mammary gland portion of an operation area of a patient, effusion can be rubbed away, accumulation of the effusion in mammary gland tissue is avoided, hematoma or blood clots are reduced, and the effusion is discharged more effectively; blood circulation and metabolism of surrounding tissues are promoted through pressing, swelling of an operation area is eliminated, postoperative pain and discomfort of a patient are relieved, swelling of the patient is relieved, and the healing process of the tissues is improved.
Owner:AFFILIATED HOSPITAL OF JINING MEDICAL UNIV

Malicious traffic remodeling method based on feature serialization

The invention relates to the technical field of network security and network simulation, and discloses a malicious traffic remodeling method based on feature serialization. The method comprises the following steps: collecting traffic data of a target network environment, extracting serialization features of a load and a time interval, and further performing statistics to obtain session flow features; according to Pareto distribution, normal distribution, logarithmic normal distribution and Poisson distribution probability distribution models, serialization features conforming to target network flow features are generated, and the probability distribution model with the highest similarity with the target network flow is selected by calculating the Euclidean distance; and finally, on the basis of the model, remodeling the load and time interval sequence of the malicious traffic, and generating the network attack traffic which is difficult to detect. According to the method, the concealment of the malicious traffic is effectively improved, so that the malicious traffic is more difficult to identify by an existing detection system; the generated malicious traffic can effectively test and evaluate the capability of the network intrusion detection system.
Owner:SICHUAN UNIV