Mnemonic Login Evaluation for Memorable, Hard-to-Guess Credentials
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for selecting login data lack sophistication, leading to insecure choices due to ease of guessing or forgetting, and fail to provide adequate support for users with diverse language preferences or cognitive challenges.
Innovation Solution
A multi-perspective evaluation system using trained machine-learning models generates mnemonic data to assist memory and adversarially evaluates potential interpretations, enhancing security by combining assistive and adversarial techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If users are required to select complex login data for improved security, then security strength is improved, but user memory retention and ease of operation deteriorate
Solution Approach 1:
The patent introduces mnemonic data as an intermediary between the user and the complex login data. The mnemonic generation model creates simplified memory cues (images, text, or combinations) that mediate the user's interaction with complex passwords, allowing users to remember secure login data without directly memorizing the complex credentials themselves.
Solution Approach 2:
The system segments the login authentication process into two distinct components: the complex login data (password) and the simplified mnemonic data. This segmentation allows the security-critical function (complex password) to be separated from the user-facing function (simple memory cue), resolving the contradiction between security requirements and user cognitive limitations.
2Ease of operation
If users are encouraged to use simple login data for ease of operation, then ease of operation is improved, but security strength deteriorates
Solution Approach 1:
The mnemonic data serves as an intermediary that allows users to operate with simple, memorable cues while the system internally manages the complex security requirements. Users interact only with the simple mnemonic data, while the authentication system enforces strong security policies on the actual login credentials.
Solution Approach 2:
The system provides self-service by automatically generating both the complex secure login data and its corresponding simple mnemonic representation. This eliminates the need for users to manually create secure passwords or remember complex credentials, as the system serves both security and usability requirements automatically.
3Ease of operation
If mnemonic data is generated to assist memory, then user convenience is improved, but system complexity increases
Solution Approach 1:
The mnemonic generation model operates autonomously as a self-service component within the authentication system. It automatically receives login data, generates appropriate mnemonic representations, and provides them to users without requiring manual intervention or complex external processing, thereby managing complexity internally while maintaining user convenience.
Solution Approach 2:
The mnemonic generation model is designed as a universal component that can handle multiple types of login data (passwords, passphrases) and generate multiple types of mnemonic representations (images, text, or combinations). This multi-functionality consolidates complexity into a single versatile module rather than requiring separate mechanisms for different scenarios.
4Reliability
If adversarial evaluation is performed to improve security, then security strength is improved, but processing time increases
Solution Approach 1:
The adversarial evaluation is performed as a preliminary action during the mnemonic generation phase, before the actual authentication occurs. The mnemonic evaluation model proactively assesses potential security weaknesses in the generated mnemonics and adjusts them beforehand, preventing security issues rather than detecting them during authentication, thus minimizing time loss during actual login operations.
Data Source
AI summary
A multi-perspective login data evaluation computing system receives candidate login data for a secured service or a secured computing system. The multi-perspective evaluation system includes a mnemonic generation model and a mnemonic evaluation model. The mnemonic generation model generates, based on features of the candidate login data, candidate mnemonic data that includes media data associated with the candidate login data. The mnemonic evaluation model generates, based on features of the mnemonic guess features, login guess data that includes at least one text string or other login guess data object that describes a potential interpretation of the candidate mnemonic data. The multi-perspective evaluation system provides one or more of the candidate mnemonic data or the login guess data to an additional computing system. In some cases, the multi-perspective evaluation system provides user profile data that is based on the candidate login data.