5 matches found
Spiritual-Spell-Red-Teaming
๐๓ ๓ ๓ ๓ ง๓ ๓ ฉ๓ ๓ ฅ๓ ข๓ ๓ ๓ ๓ ข๓ ฃ๓ ๓ ๓ ๓ ๓ ๓ ค๓ ฉ๓ ๓ ๓ ฉ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ค๓ ๓ ๓ ฉ๓ ๓ ๓ ๓ ๓ ฃ๓ ค๓ ๓ ๓ ฃ๓ ๓ ๓ ๓ ๓ ๓ ค๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ฃ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ค๓ ๓ ๓ ๓ ฃ๓ ๓ ๓ ๓ ๓ ๓ ข๓ ๓ ฃ๓ ๓ ๓ ค๓ ๓ ง๓ ๓ ค๓ ๓ ๓ ฃ๓ ค๓ ๓ ๓ ๓ ๓ ๏ธ๏ธ๓ ๓ ๓ ฅ๓ ๓ ๓ ข๓ ๓ ๓ ต๓ พ๓ น๓ ๓ ๓ ๓ ๓ ฃ๓ ค๓ ฅ๓ ๓ ๓ ๓ ๓ ๓ ๓ ฃ๓ ง๓ ๓ ๓ ค๓ ๓ ข๓ ๓ ง๓ ๓ ๓ ข๓ ๓ ๓ ๓ ๓ ๓ ๓ ฆ๓ ๓ ๓ ๓ ฃ๓ ค๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ จ๓ ๓ ๓ ข๓ ค๓ ๓ ๓ ๓ ๓ ผ๓ ๓ ๓ ๓ ข๓ ๓ ๓ ๓ ๓ ๓ ง๓ ๓ ค๓ ๓ ๓ ผ๓ ฟ๓ ๓ ๓ ง๓ ๓ ๓ ๓ ง๓ ข๓ ๓ ค๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ฑ๓ พ๓ ๓ ๓ ธ๓ น๓ พ๓ ท๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ฃ๓ ๓ ฃ๓ ฃ๓ ๓ ฆ๓ ๓ ๓ ฉ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ฉ๓ ๓ ๓ ๓ ๓ ๓ ๓ ง๓ ฃ๓ ๓ ๓ ๓ ฃ๓ ๓ ข๓ ๓ ก๓ ฅ๓ ๓ ฃ๓ ค๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ข๓ ๓ ฉ๓ ๓ ๓ ฅ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ๓ ฃ๓ ค๓ ๓ ข๓ ๓ ๓ ฉ...
redthread
RedThread Find the exploit. Judge it. Draft the fix. Prove what changed. RedThread is a CLI-first framework for testing LLM systems, validating failures, and turning confirmed vulnerabilities into evidence-backed defense candidates. It is built for teams who need more than a one-off jailbreak dem...
cerebro-red-v2
CEREBRO-RED v2 Research Edition Autonomous Local LLM Red Teaming Suite A research-grade framework for automated vulnerability discovery in local LLMs using Agentic Fuzzing and Adaptive Adversarial Mutation AAM. Research Goals Implement PAIR Algorithm Prompt Automatic Iterative Refinement from...
gemini-2.5-pro-nf-tables-red-teaming
Gemini 2.5 Pro nftables Red Teaming Case Study CVE-2023-32233 LLM Safety Research | Responsible Disclosure | AI Alignment Evaluation Researcher : Niranj R Mahaswar Destawell Google AI Vulnerability Reward Program : 889286 โ Out of Scope Summary This repository documents a comparative LLM red...
Generating Attacks for LLMs with GFlowNets
The rapid advancement of Large Language Models LLMs has facilitated their ubiquitous integration into various domains, leading to widespread adoption. However, this escalating trend has introduced significant security vulnerabilities, necessitating the identification and mitigation of flaws arisi...