3 repos
Awesome GitHub RepositoriesAdversarial Security Research
Resources and methodologies for identifying, simulating, and reporting security vulnerabilities within AI systems.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Adversarial Security Research. Refine with filters or upvote what's useful.
Awesome Adversarial Security Research GitHub Repositories
We'll search the best matching repositories with AI.
- dair-ai/Prompt-Engineering-Guide
This project is a comprehensive educational resource and knowledge base dedicated to the development and application of large language models and autonomous agentic systems. It provides a structured framework for understanding prompt engineering, context management, and the architectural patterns required to build task
MDXagentagentsai-agents - NationalSecurityAgency/ghidra
Ghidra is a software reverse engineering suite designed to analyze compiled binaries and reconstruct program logic without access to original source code. It provides an interactive environment for disassembly and decompilation, utilizing a platform-independent intermediate representation to maintain consistency across
Javadisassemblerreverse-engineeringsoftware-analysis - PlexPt/awesome-chatgpt-prompts-zh
This project is a community-driven library of structured text inputs designed to guide large language models into specific roles, behaviors, and operational modes. It functions as a comprehensive repository of prompt engineering resources, providing reusable templates that allow users to override default model tendenci
chat-gptchatgptchatgpt3
Explore sub-tags
- Adversarial Prompt DatasetsCollections of prompts designed to test model safety boundaries and identify potential vulnerabilities in guardrail implementations.
- Adversarial Simulation EnvironmentsInteractive environments used to test model robustness against jailbreaking, prompt injection, and other adversarial inputs.
- Prompt Injection TechniquesMethods used to bypass safety filters and operational constraints through adversarial input patterns.
- Vulnerability Disclosure Reports