DecodingTrust
by AI-secure
A Comprehensive Assessment of Trustworthiness in GPT Models
AI summary
GPT model trustworthiness assessor
An assessment tool for evaluating trustworthiness in GPT models across various aspects such as toxicity, bias, robustness, and fairness.
- stars
- 267
- forks
- 57
- watching
- 6
Similar projects
Found by comparing what the projects do, not just their names.
Trust Assessment Toolkit
A toolkit for assessing trustworthiness in large language models
Information extractor
Extracts and stores information from various sources using AI models to generate answers.
Risk assessment tool
Empowers security professionals to identify risks in generative AI systems by providing a framework for proactive risk assessment and red teaming.
AI Explainability Tool
A toolkit for explaining complex AI models and data-driven insights
Sentiment analyzer
An application providing sentiment analysis tools for financial assets and securities using GPT models and Google search results
Verifier
An implementation of a DeepPoly-based verifier for robustness analysis in deep neural networks
Programming assistant
A repository of GPT-powered programming assistants to support developers in their work.
Code Review Bot
Reviews Pull/Merge Requests using AI-powered chatbot
GPT analyst toolset
A resource repository providing tools and guides for analyzing and reverse engineering GPT models.
Source code auditor
A tool to identify potential security flaws in source code using static analysis and regular expressions.
Code scanner
An automated code review tool powered by Large Language Models that scans source code for potential issues and provides feedback
Robustness framework
Provides a framework for computing tight certificates of adversarial robustness for randomly smoothed classifiers.
Mqtt Tester
A tool for penetration testing and security assessment of MQTT brokers using various exploitation techniques.
GPT-4V evaluation tool
An evaluation framework for GPT-4V models using data from An Early Evaluation of GPT-4V(ision)
Robustness tester
A toolbox for researching and evaluating robustness against attacks on machine learning models
