1 dépôt
Awesome GitHub RepositoriesAdversarial Prompt Pattern Analysis
Analysis of syntactic and structural markers to identify adversarial attack strategies in text.
Distinct from Pattern Analysis: Focuses on adversarial prompt structures rather than general string patterns like palindromes.
Explore 1 awesome GitHub repository matching software engineering & architecture · Adversarial Prompt Pattern Analysis. Refine with filters or upvote what's useful.
Awesome Adversarial Prompt Pattern Analysis GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- verazuo/jailbreak_llms
verazuo/jailbreak_llms
3,563Voir sur GitHubThis project is a comprehensive ecosystem of frameworks, toolkits, and datasets designed to evaluate model vulnerabilities and analyze jailbreak patterns. It serves as an adversarial testing framework and research toolkit for measuring the effectiveness of safety guardrails in large language models. The system includes a library of real-world prompt injection datasets harvested from social media to study bypass strategies. It provides specialized tools for semantic attack analysis and prompt visualization, allowing for the mapping of relationships between adversarial prompts to discover commo
Extracts common syntactic and structural markers from prompt collections to identify specific jailbreak techniques.
Jupyter Notebookchatgptjailbreakjailbreaking
