Multi-turn LLM red-teaming framework using PAIR to measure behavioral drift and alignment decay across adversarial turns.

adversarial-attacks ai-alignment ai-safety ai-security compliance hedging jailbreak jailbreak-tweaks llm llm-evals llm-evaluation-framework loop-engineering streamlit
4 Open Issues Need Help Last updated: Jul 5, 2026

Open Issues Need Help

View All on GitHub
help wanted good first issue

Multi-turn LLM red-teaming framework using PAIR to measure behavioral drift and alignment decay across adversarial turns.

Python
#adversarial-attacks#ai-alignment#ai-safety#ai-security#compliance#hedging#jailbreak#jailbreak-tweaks#llm#llm-evals#llm-evaluation-framework#loop-engineering#streamlit
help wanted good first issue

Multi-turn LLM red-teaming framework using PAIR to measure behavioral drift and alignment decay across adversarial turns.

Python
#adversarial-attacks#ai-alignment#ai-safety#ai-security#compliance#hedging#jailbreak#jailbreak-tweaks#llm#llm-evals#llm-evaluation-framework#loop-engineering#streamlit
help wanted good first issue

Multi-turn LLM red-teaming framework using PAIR to measure behavioral drift and alignment decay across adversarial turns.

Python
#adversarial-attacks#ai-alignment#ai-safety#ai-security#compliance#hedging#jailbreak#jailbreak-tweaks#llm#llm-evals#llm-evaluation-framework#loop-engineering#streamlit
help wanted good first issue

Multi-turn LLM red-teaming framework using PAIR to measure behavioral drift and alignment decay across adversarial turns.

Python
#adversarial-attacks#ai-alignment#ai-safety#ai-security#compliance#hedging#jailbreak#jailbreak-tweaks#llm#llm-evals#llm-evaluation-framework#loop-engineering#streamlit