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

476 results about "White box" patented technology

A white box (or glass box, clear box, or open box) is a subsystem whose internals can be viewed but usually not altered. Having access to the subsystem internals in general makes the subsystem easier to understand but also easier to hack; for example, if a programmer can examine source code, weaknesses in an algorithm are much easier to discover. That makes white-box testing much more effective than black-box testing but considerably more difficult from the sophistication needed on the part of the tester to understand the subsystem.

Rolling bearing residual life prediction method and system based on convolution white box

The invention belongs to the technical field of bearing residual service life detection, and discloses a rolling bearing residual service life prediction method and system based on a convolution white box. According to the method, time domain and frequency domain feature extraction, noise reduction processing and health state and degradation state division are carried out on an original vibration signal, and deep neural network training is carried out in combination with a Weibull-MSE loss function, so that prediction of RUL conforms to the actual degradation process of a bearing; and synchronous extraction of long-time dependence information and local degradation characteristics of the bearing signal is completed through a convolution CRATE network architecture fusing an expansion causal convolution attention mechanism DCA and a multi-scale convolution MSC. According to the method, the accuracy of RUL prediction is improved in combination with health state evaluation, the local feature extraction capability is enhanced, the local modeling capability of the model is improved through multi-scale information fusion, and the interpretability and the prediction credibility are improved through a CRATE structure.
Owner:SHANDONG UNIV OF SCI & TECH

AI training paradigm based on Personalized Heuristic QA 3D Self-study Method trains AI for Personalized education and General Rational AI System: Hybrid AGRINN (Artificial General Rational Intelligent Neural Network)

XI Personalized Heuristic QA 3D Self-Study Method provides systematic training through personalized heuristic question-answer iterations and 3D (vertical, horizontal and application) integration learning, tutoring learners to effectively learn on their own: acquire knowledge, understand underlying rules, fill in gaps in prior studies, and build up learners' self-Study ability. XI paradigm based on the method trains an LLM for personalized education, deductive reasoning, problem-solving, Integration-Innovation system: Hybrid AGRINN (Artificial General Rational Intelligent Neural Network). The system comprises a white-box AGRINN and a black-box AGRINN trained through it. The white-box AGRINN comprises three layers: ARICNN (Artificial Rational Intelligence Central Neural Network), Integration Hubs and Clustered Modules. ARICNN comprises Knowledge, Rule, Tool and Method subnetworks. Each Clustered Module is a template supported adaptable unit with clusters of QA-iterations, tutoring learners to tackle specific problem types and their variations. Each Integration Hub links a group of clustered modules that utilizes common elements of ARICNN.
Owner:XI WENDY WUSAN

Large language model distillation method, device and equipment and storage medium

The invention discloses a large language model distillation method, device and equipment and a storage medium, and relates to the technical field of computers, and the large language model distillation method comprises the steps: determining the teacher occupancy measure of a teacher model and the student occupancy measure of a student model based on a Markov decision process and a teacher model generation process; performing loss function definition through the teacher occupation measure, the student occupation measure and the JS divergence, and determining a training loss function of the student model; and training the student model according to an expert data set, a target discriminator and the training loss function to obtain a target distillation model, and performing a language processing task through the target distillation model. Through the mode, the distillation process combines the advantages of black box knowledge distillation and white box knowledge distillation, the time cost and hardware cost of model distillation are reduced, and the model performance and universality of the small distillation model are ensured.
Owner:PENG CHENG LAB

Conditional diffusion model-based confrontation sample purification method

The invention discloses an adversarial sample purification method based on a conditional diffusion model. The adversarial sample purification method comprises the following steps: acquiring a clean sample data set containing clean samples; attacking the classification model by using a white-box attack algorithm, and generating a pair of confrontation samples for each clean sample; performing one-to-one pairing on the clean samples and the adversarial samples to form a training data set; the method comprises the following steps of: obtaining a pre-trained Stable Diffusion model; designing a fine tuning process and a fine tuning loss function; and S6, presetting an iteration round and a batch size, and finely adjusting network parameters of a cross attention layer in the Stable Diffusion model by using the training data set to obtain a finely-adjusted conditional diffusion model for purification of an adversarial sample. According to the method, the adversarial sample is used as conditional information to be input into the Unet neural network to guide model learning, so that the model can learn the characteristics of adversarial disturbance, and the calculation efficiency, robustness and stability can be improved.
Owner:SHANGHAI CHENGDIAN FUZHI TECH CO LTD

Large-model end-to-end distillation deployment method, device and equipment for low-computing-power equipment and medium

The invention discloses a large model end-to-end distillation deployment method and device for low-computing-power equipment, equipment and a medium, and relates to the field of artificial intelligence, and the method comprises the steps: in a computing cluster, determining a first target data set and a target student model, and deploying a distillation model training framework; deploying a preset large language model to a computing cluster by using a first preset large model reasoning framework, and determining the deployed preset large language model as a teacher model; if the distillation model training framework is a black box knowledge distillation framework, determining a second target data set based on the teacher model and the first target data set, and distilling the target student model by using the second target data set to obtain a distillation model; if the distillation model training framework is a white-box knowledge distillation framework, distilling the target student model based on a teacher model to obtain a distillation model; and deploying the distillation model to target equipment based on a second preset large model reasoning framework. Therefore, the efficiency of accessing the large language model can be improved.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Network traffic confrontation defense method based on heuristic ant colony optimization

The invention discloses a network flow confrontation defense method based on heuristic ant colony optimization, and belongs to the technical field of network security and privacy protection. According to the method, a self-adaptive disturbance generation strategy is designed according to spatial and temporal features of a network traffic trajectory, a disturbance injection rule meeting real-time constraint and direction consistency is established, an integrated substitution model is constructed, a feature fusion mechanism of spatial convolution, time sequence circulation and noise reduction coding is used, and a traffic fingerprint identification model with strong generalization ability is generated. An improved ant colony optimization algorithm is adopted to improve the disturbance search capability, and a batch processing method and a universal patch scoring mechanism are integrated to improve the defense universality of samples among different network flows. The method can be directly applied to a black box scene of real-time communication, gradient information or white box access permission of a target model is not needed, the attack recognition suppression rate exceeding 90% is achieved when only 20% of bandwidth overhead is increased, defense universality and deployment feasibility are remarkably improved, and meanwhile disturbance overhead is reduced.
Owner:HUNAN UNIV

Track prediction model robustness enhancement method based on dynamic subspace projection decomposition

The invention relates to a trajectory prediction model robustness enhancement method based on dynamic subspace projection decomposition. Comprising the following steps: firstly, extracting hidden layer semantic features containing historical tracks and map topology through a multi-modal feature encoder; secondly, constructing a dynamic routing mechanism based on scene self-adaption, and calculating projection weights of input features on a plurality of expert subspaces; then, executing truncation projection operation based on orthogonal decomposition, retaining core semantics located in a low-dimensional space, and filtering out adversarial disturbance located in an orthogonal complementary space; and finally, introducing a feature consistency constraint training mechanism, taking the reconstructed features of the clean sample as anchor points, and compulsively aligning the purified features of the confrontation sample with the anchor points. Compared with the prior art, the method has the advantages that the robustness of the model in white box gradient attack, black box query attack and physical semantic deception scenes is remarkably improved through feature purification of a physical level and structured consistency constraint, and the prediction reliability of the automatic driving system is ensured.
Owner:TONGJI UNIV

Systems and methods for whitebox device binding

A method is disclosed. The method includes receiving, by a user device, an encrypted message from a server computer. The encrypted message is a message encrypted with a master secret key or a key derived from the master secret key. The user device signs the encrypted message with a secure element private key. The user device, using a whitebox, cryptographically recovers a secure element public key from a certified key using a server computer public key. The certified key is certified by the server computer and based on at least the secure element public key. The user device, using the whitebox, cryptographically recovers the encrypted message from the signed encrypted message using the secure element public key. The user device, using the whitebox, decrypts the encrypted message using the master secret key or the key derived from the master secret key in the whitebox to obtain the message.
Owner:VISA INTERNATIONAL SERVICE ASSOCIATION

Behavioral prediction and boundary settings, control and safety assurance of ML and AI systems

Typical autonomous systems implement black-box models for tasks such as motion detection and triaging failure events, and as a result are unable to provide an explanation for its input features. An explainable framework may utilize one or more explainable white-box architectures. Explainable models allow for a new set of capabilities in industrial, commercial, and non-commercial applications, such as behavioral prediction and boundary settings, and therefore may provide additional safety mechanisms to be a part of the control loop of automated machinery, apparatus, and systems. An embodiment may provide a practical solution for the safe operation of automated machinery and systems based on the anticipation and prediction of consequences. The ability to guarantee a safe mode of operation in an autonomous system which may include machinery and robots which interact with human beings is a major unresolved problem which may be solved by an exemplary explainable framework.
Owner:UMNAI LTD

SDK (Software Development Kit) white box test method

The invention provides an SDK white-box testing method, which comprises the following steps that: a shell project and a target SDK are created, the shell project comprises a running environment of an operating system, and the target SDK is a to-be-tested object; and providing the to-be-tested case code writing template for the user to obtain a target test case which is written by the user based on codes of the to-be-tested case code writing template and is used for carrying out white-box testing on the target SDK. And importing the target test case into the shell project to obtain a test APP suitable for operation of an operating system. And running the test APP in the operating system to perform white-box test on the target SDK. According to the method and the device, the white-box test aiming at the SDK can be realized under the condition of not depending on professional code programming capability of a user.
Owner:CHINA MOBILE INTERNET CO LTD +1

Intelligent power grid dispatching instruction optimization system based on semantic analysis

The invention discloses an intelligent power grid dispatching instruction optimization system based on semantic analysis, relates to the technical field of power grid dispatching instruction optimization, realizes the conversion of dispatching instruction generation from black box output to white box reasoning, constructs a new intelligent dispatching normal form with deep integration of knowledge driving and data driving, and improves the intelligent dispatching efficiency. The automation level, decision reliability and operation safety of power grid dispatching are remarkably improved, and the method has outstanding innovativeness and wide engineering application prospects.
Owner:HUANGHUA POWER SUPPLY COMPANY OF STATE GRID QINGHAI ELECTRIC POWER +1

Temperature alarm method and device for bus duct, terminal and storage medium

The invention provides a temperature alarm method and device for a bus duct, a terminal and a storage medium. The method comprises the following steps: constructing a white box model for representing a corresponding relation between bus current and bus temperature rise according to an equipment mechanism modeling mode and a thermodynamic principle; constructing an initial grey box model between the bus current and the bus temperature rise based on the white box model, and training the initial grey box model based on a machine learning algorithm to obtain a trained target grey box model; predicting a dynamic temperature rise threshold value and a predicted temperature value corresponding to the current current value by using the target grey box model; the current current value is a current value corresponding to a currently monitored actual temperature value of the bus duct, comparing a difference value between the actual temperature value and the predicted temperature value with a dynamic temperature rise threshold to obtain a comparison result, and determining whether to trigger an alarm based on the comparison result. The dynamic threshold value is generated through model prediction, and the problem that the abnormal temperature rise of the bus cannot be accurately fed back due to manual configuration of the static threshold value is solved.
Owner:SHENZHEN XBROTHER TECH

Method and device for detecting information safety production consistency of vehicle and electronic equipment

The invention relates to the technical field of vehicles, in particular to a vehicle information safety production consistency detection method and device and electronic equipment.The method comprises the steps that a target part injected with first secret key information is received, black box testing is conducted on the target part, and a black box testing result is obtained, and if the black box test result meets a first preset test condition, performing a white box test on the target part to generate a white box test result of the target part, and if the white box test result meets a second preset condition, generating safety test information of the target part. Therefore, the problem that the production consistency of part information safety cannot be guaranteed due to the fact that whether the debugging port of the part is effectively closed or not cannot be verified through a detection method in the related technology is solved, effective closing of the debugging port is verified through the method of carrying out secret key injection and penetration testing on the part, and therefore the production consistency of the part information safety is guaranteed.
Owner:CHERY AUTOMOBILE CO LTD

Method for determining generative model, electronic equipment and product

The embodiment of the invention provides a method for determining a generative model. The method includes embedding a white box watermark and a black box watermark in a generative model. Black box watermarks are first embedded into probability density functions of data abstraction in different layers of the generative model. The method also includes embedding the white box watermarks into different layers for generative model output after the embedding of the black box watermarks is completed. Model data is generated by the generative model based on predetermined trigger data. The predetermined trigger data comprises a predetermined trigger text or a predetermined trigger image. An identity associated with the generative model is determined based on the model data. By using the method, white box and black box attacks can be resisted by embedding two complementary and independent watermarks, so that double-layer protection is provided for the generative model.
Owner:DELL PROD LP

ChatGPT-based security protection software rule generation method and system

The invention provides a ChatGPT-based security protection software rule generation method and system, and relates to the field of network security threat detection, and the specific scheme is as follows: automatically crawling a threat analysis report A of an effective rule generated by other security equipment platforms, taking the effective rule of the threat analysis report A as a rule case to carry out instruction fine tuning on ChatGPT, and taking the effective rule of the ChatGPT as a rule case; generating and obtaining a sample fine tuning GPT model; obtaining a threat analysis report B of the security equipment to be protected, initiating a request for ChatGPT based on the sample fine tuning GPT model, analyzing the threat analysis report B by ChatGPT according to the request to generate a threat detection rule, and converting the threat detection rule into a grammar rule of security protection software; and performing simulation attack test and white-box test based on the grammar rules, and screening out grammar rules which do not pass the test to obtain general grammar rules of the security protection software. According to the method, the problem that the attack response is slow in the prior art is solved, the threat detection rule is automatically designed and generated, and the use cost is reduced.
Owner:GUANGZHOU UNIVERSITY

Client identity authentication security evaluation method and system combined with adversarial sample simulation

The invention provides a client identity authentication security evaluation method and system combined with adversarial sample simulation, and relates to the technical field of information security. According to the invention, end-cloud integrated evaluation is carried out under a white-box and black-box threat model for multi-mode identification objects of human face, voiceprint, fingerprint and behavior characteristics. The method comprises the steps of establishing reference performance through legal samples, generating transferable adversarial input, performing secure injection on a communication layer, calculating a robustness index, performing adaptive optimization, performing differential evaluation on protection effectiveness under protection configuration starting and non-starting, and performing risk grading and reinforcement according to a result. And finally, outputting a reproducible security and compliance conclusion through differential privacy and federal evaluation.
Owner:CHENGDU CHUANGXIN HUATONG INFORMATION TECH CO LTD

Generative attack and defense confrontation method based on domain self-adaption

The invention provides a domain self-adaption-based generative attack and defense confrontation method. Directional interference on a black-box intelligent system is realized by constructing a generative confrontation network framework. The method takes a domain self-adaption theory in transfer learning as a core, builds a dynamic mapping relation between a white box model group and a black box target system, designs a dual-channel generative adversarial network, jointly supervises sample authenticity and cross-model transfer consistency through cross entropy loss and KL divergence constraint, builds a dynamic boundary feedback system, and achieves the dynamic boundary feedback. And a disturbance generation strategy of the generator is adjusted according to the real-time attack effect, and a self-adaptive attack and defense game closed loop is formed. Compared with a traditional black box attack method, the method has the advantages that migration robustness of an adversarial sample in a model heterogeneous scene is remarkably improved, stable attack efficiency can still be maintained when a defense system has protection mechanisms such as adversarial training and input reconstruction, and the method can be applied to the fields such as penetration testing of an intelligent security system and the like. And a technical support is provided for vulnerability evaluation of the intelligent system in a complex environment.
Owner:CHINA ACAD OF AEROSPACE SCI & TECH INNOVATION

Performance prediction method for intelligent computing system

The invention discloses a performance prediction method for an intelligent computing system, and the method achieves the efficient and explainable performance prediction through mixed analysis modeling. The method mainly comprises the steps of performing tracking and programmed synthesis on a target deep learning model, and generating a final operator graph containing a complete calculation and communication operation sequence; a dynamic overlap analysis model based on available parallelism is adopted, independent calculation and memory access efficiency is predicted in combination with a machine learning method, and GPU operator execution delay is accurately estimated; based on a configurable network topology, applying a queuing theory network model, and carrying out white box type modeling on queuing and transmission delay of communication operation in each node in a network path; and the calculation and communication prediction delays of the operators are aggregated according to the scheduling characteristics of the distributed strategy to obtain the final system end-to-end delay. The method provided by the invention can ensure the precision while remarkably shortening the prediction time, and has the advantages of high efficiency, high interpretability and the like.
Owner:ZHEJIANG UNIV

Multi-modal large model confrontation safety detection system and method

The invention discloses a multi-modal large model confrontation safety detection system and method, and aims to evaluate the robustness and confrontation safety of a multi-modal large model. According to the method, the input data is processed through the single-mode encoder, and the adversarial disturbance is applied to the obtained embedded representation to weaken the collaborative consistency among the multi-mode data, so that the multi-mode adversarial sample is constructed and is used for detecting the accuracy of the multi-mode large model when the multi-mode large model executes a downstream task. The method is suitable for a non-white-box test scene, the difficulty of model security assessment is effectively reduced, and the universality of assessment is improved; the proposed multi-modal confrontation sample collaborative generation scheme can effectively utilize the potential relation among the modal data to realize more comprehensive confrontation security detection; in addition, the method has good expandability, and supports generation of adversarial samples of various multi-modal data including texts and images, texts and audios, texts and silent videos and the like.
Owner:ZHEJIANG UNIV

System and method for automated verification of battery management system

The present disclosure relates to a system and method for automated verification of a battery management system for a battery pack, an energy storage device, etc., and the problem to be solved is to enable automated verification for items that should be determined by modifying internal variable information or verifying results with the internal variable information during white box verification of the internal architecture logic of BMS firmware of an ESS. There is provided a system for automated verification of a BMS, including a device for automated verification configured to create a test case sequence for testing firmware operation items of the BMS, perform a simulation on the BMS, and model operation items of the BMS, a BMS controller that is connected to the device for automated verification and controls the BMS to operate by applying modeled data for the operation items to the BMS, and a BMS internal variable acquirer that acquires internal variable information of the BMS during execution of the simulation.
Owner:SAMSUNG SDI CO LTD

White box test method and device, storage medium and computer equipment

The invention discloses a white box test method and device, a storage medium and computer equipment. Relates to the technical field of software testing, the financial field and the medical field. The technical problem that an existing white box testing method is low in efficiency is mainly solved. The method mainly comprises the steps that historical test coverage information and an incremental function of a to-be-tested version source code are pulled, and the historical test coverage information is determined based on a test coverage rate merging result of a previous version source code of the to-be-tested version source code; respectively generating a function call relation graph and a function control flow chart of the incremental function; screening the incremental function according to the historical test coverage information, the function call relation graph and the function control flow chart, and creating a test case according to a screening result; and executing the test case to perform white-box test on the source code of the version to be tested, and generating a test result of the source code of the version to be tested. The method is mainly used for white-box testing.
Owner:PING AN INT FINANCIAL LEASING CO LTD

Iterative satellite internet confrontation method based on momentum

The invention discloses an iterative satellite internet confrontation method based on momentum, and mainly solves the problem of low success rate of black box migration attack in the existing method. According to the method, a momentum item is introduced in an iterative optimization process of adversarial sample generation and is used for recording a historical direction of gradient updating. According to the momentum iteration method, the gradient updating direction in the adversarial sample generation process can be more stable, meanwhile, the adversarial sample is prevented from falling into a local extreme point of an optimization problem, the mutual restriction of the white box attack effect and the migration capability of the adversarial sample generated by the existing method is effectively relieved, and the black box migration attack success rate is improved.
Owner:CHENGDU EAGLE INFORMATION TECH CO LTD

Adversarial sample generation method and device for face forgery detection model

The invention discloses an adversarial sample generation method and device for a face forgery detection model. The method comprises the following steps: obtaining a real category attention graph and a false category attention graph of an original sample by using a white-box face counterfeiting detection model, fusing the real category attention graph and the false category attention graph to obtain a fused attention graph, and processing the fused attention graph to obtain a dual hard mask; generating global disturbance of the original sample by using a spatial domain disturbance generator obtained by pre-training; cutting the global disturbance by using the dual hard mask to obtain local disturbance; and superposing the local disturbance to the original sample to obtain an adversarial sample. According to the scheme, the face forgery detection model can be attacked from a real area and a false area, a high attack success rate is achieved for the white box face forgery detection model and the black box face forgery detection model, and the attack effect of the confrontation sample is improved.
Owner:PEOPLE CN CO LTD

Multi-objective collaborative optimization parameter setting method for blasting vibration and dust control

The invention discloses a blasting vibration and dust control-oriented multi-objective collaborative optimization parameter setting method, which comprises the following steps of: training a neural network model capable of predicting a complete vibration time travel curve and a three-dimensional dust concentration field on the basis of a training sample containing geological conditions, blasting parameters and an actual blasting effect; the model is used for carrying out multi-target optimization on a target function containing four indexes of vibration, dust, cost and regulation compliance through a preset evolutionary algorithm, a Pareto optimal solution set composed of a plurality of non-dominated parameter schemes is obtained, the schemes in the optimal solution set are analyzed through a preset explanation algorithm, and the optimal solution set is obtained. The influence and contribution degree of each blasting parameter on a prediction result are quantified, so that a black box model is converted into an interpretable white box decision; according to the method, the problems that a traditional method is difficult to balance multiple conflict targets and the decision-making process is opaque are solved, and an optimal blasting parameter scheme considering safety, environmental protection and cost effectiveness is provided for blasting operation.
Owner:CHINA RAILWAY 17TH BUREAU GRP URBAN CONSTR CO LTD

Terminal software comprehensive analysis method and system based on artificial intelligence

The invention relates to a terminal software comprehensive analysis method and system based on artificial intelligence, and the method comprises the steps: obtaining the hardware configuration information of a terminal device and the performance index data of terminal software, carrying out the feature extraction, carrying out the clustering analysis in combination with a historical sample, and generating a software parameter configuration suggestion through a reinforcement learning tuning model, and further performing security evaluation through a white box constraint rule and a black box performance prediction model, and finally generating a software optimization scheme and monitoring performance change to optimize the model. According to the method, the internal structure and the potential mode of the obtained data can be mined, intelligent adjustment and optimization are realized in different hardware environments, meanwhile, dynamic optimization of safety and performance is considered, and the operation efficiency and the stability of terminal software are improved.
Owner:ANHUI INSIGHT FUTURE TECHNOLOGY DEVELOPMENT CO LTD

Model enhancement-based variance reduction enhanced adversarial sample generation method

The invention provides a variance reduction enhanced confrontation sample generation method based on model enhancement, which effectively improves black box aggressiveness while keeping excellent white box attack performance, and is not easy to defend by some existing confrontation attack defense methods. The method comprises the following steps: performing model enhancement on a victim model by adopting an input transformation pool to obtain an enhanced model set, and calculating an integrated gradient of the enhanced model set through K times of iteration; a new enhancement model is obtained by inputting the transformation pool, and the internal gradient of the internal adversarial sample and the internal gradient of the external adversarial sample are calculated according to the new enhancement model; obtaining a cumulative gradient for updating the internal adversarial sample, and updating the internal adversarial sample by using the cumulative gradient; using the last internal cumulative gradient to update the external gradient, and finally using the external gradient to update the external adversarial sample; and repeating the above steps for T times, and once iteration is completed, successfully generating an adversarial sample.
Owner:ZHEJIANG GONGSHANG UNIVERSITY

Data-free black box adversarial sample generation method based on attention enhancement

ActiveCN119539024AMeet the requirements of real-world scenariosOvercoming poor diversityInternal combustion piston enginesBiological modelsSynthetic dataInformatics
The invention relates to the field of artificial intelligence confrontation technology and the like, and discloses a data-free black box confrontation sample generation method based on attention enhancement, which comprises the following steps: randomly sampling a noise space, and generating synthetic data # imgabs0 # by an input generator; querying decision output of a black box target model # imgabs2 by using the synthetic data # imgabs1 #, and caching an input-output pair; enhancing the substitution model by using an attention enhancement module, and training the enhanced substitution model; training a generator by using a joint structure information learning strategy; the cached input and output pairs are replayed, and the enhanced substitution model is further trained; constructing an adversarial sample on the enhanced substitution model by applying a white-box attack strategy, and migrating to a black-box target model to implement attack; the problems that an existing substitution model is low in learning efficiency for different synthetic data, the synthetic data generated by the generator is poor in diversity, and the substitution model is low in training efficiency are solved, and by optimizing the substitution model and the generator learning strategy, the optimized substitution model accurately simulates black box target model decision output.
Owner:SICHUAN UNIV

Adversarial sample generation method and system based on dynamic pseudo labels

PendingCN120596920AAlgorithmWhite box
The invention provides an adversarial sample generation method and system based on a dynamic pseudo tag, and the method comprises the steps: calculating the classification confidence distribution of a sample x based on a white box model, and determining a misjudgment category with the highest confidence as a pseudo tag; calculating a synthetic gradient of a real label and the pseudo label loss function; based on the obtained synthetic gradient, obtaining an adversarial sample xadv; and updating the sample x by using the obtained adversarial sample xadd, repeating the steps, iterating for a preset number of times T, and outputting an adversarial sample xadv. According to the method, the mobility and the generation efficiency of the adversarial sample are improved.
Owner:CHINESE PEOPLES LIBERATION ARMY ARMY ARTILLERY & AIR DEFENSE ACAD

AI-driven full-scene intelligent test platform

The invention discloses an AI-driven full-scene intelligent test platform which comprises the following steps: performing static scanning on a target code under the triggering of a code submission event through a code static scanning module to generate a scanning result, and then inputting the scanning result into a pre-trained first AI model to obtain code quality evaluation data. And generating a white box test case through a white box case generation module. In addition, a black box test case is generated through a black box case generation module. An automatic script generation module inputs the black box test case into a pre-trained fourth AI model to generate an automatic test script; and finally, running the white box test case and the automatic test script to obtain an original test report. And inputting the original test report into a pre-trained fifth AI model through a result analysis module, and generating defect distribution data and test suggestion data. The full-scene test coverage of the software life cycle is realized, the test of each link of the software is comprehensively and systematically covered, and the test efficiency is improved.
Owner:WUHAN SHIP COMM RES INST (NO 722 RES INST OF CHINA STATE SHIPBUILDING CORP)

Anti-noise semantic communication method based on supervised discriminant learning

The invention relates to an anti-noise semantic communication method based on supervised discriminant learning, and belongs to the technical field of communication. For the problems of semantic noise and channel noise in image transmission, a deep supervision network is introduced at a semantic task execution end, a supervision layer is additionally arranged behind a hidden layer, and high-quality middle layer features are extracted, so that semantic feature representation is learned; a composite loss function containing terminal loss and adjoint loss is designed, the adjoint loss is introduced into a prototype consistent loss function, and semantic noise influence is reduced through maximum separation constraint; according to the method, the priority of task execution and data recovery is adjusted according to the SNR value so as to adapt to different communication conditions; furthermore, semantic noise is generated by adopting a white box attack method, and the anti-noise performance is enhanced by utilizing a supervision layer output result on the premise of not changing the structure of the original deep learning model; a loss function is designed from the semantic feature level, the anti-noise performance is further enhanced, and data recovery and task execution are both considered.
Owner:CHONGQING UNIV OF POSTS & TELECOMM