Pinned Loading

1. ai-safety-policy-translation ai-safety-policy-translation Public

   Framework for translating LLM safety benchmark findings into deployment guidance — evidence-gated tooling with a hard safety mechanism against citing mock/simulated data as real findings. Evidence …

   Python 1

2. cross-lingual-llm-safety-eval cross-lingual-llm-safety-eval Public

   A multilingual benchmark for evaluating LLM safety, robustness, and refusal behavior across languages and frontier models.

   Python 1

3. satya-procurement-integrity satya-procurement-integrity Public

   Python 1

4. SentinelAI SentinelAI Public

   Cross-lingual LLM safety evaluation framework testing whether refusal behavior holds consistently across English, Hindi, Mandarin, Tamil, and Malay. Pilot v1 complete — includes a full technical re…

   Python 1

5. technical-ai-safety-experiment technical-ai-safety-experiment Public

   Systematic evaluation of jailbreak and prompt-injection attacks and defense strategies across open-source and commercial LLMs — 9 guardrail strategies, statistically-grounded comparison (Wilson/boo…

   Python 1