CoinflipForSafety SEML-Lab/JudgeStressTest Viewer • Updated Mar 11 • 971 • 57 • 1 SEML-Lab/ReliableBench Viewer • Updated Mar 11 • 43 • 63 • 1 SEML-Lab/CoinflipForSafety Viewer • Updated Mar 11 • 6.56k • 82 • 1 A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness Paper • 2603.06594 • Published Feb 4 • 1
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness Paper • 2603.06594 • Published Feb 4 • 1
IHO Attacker models of "Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs" SEML-Lab/IHO-Llama-3-8B-Instruct Updated Jun 3 • 84 SEML-Lab/IHO-CircuitBreaker-Llama-3-8B-PolyGuard Updated Jun 3 • 10 SEML-Lab/IHO-Qwen2.5-32B-Instruct Updated Jun 3 • 12 SEML-Lab/IHO-Qwen2.5-7B-Instruct-PolyGuard Updated Jun 3 • 8
CoinflipForSafety SEML-Lab/JudgeStressTest Viewer • Updated Mar 11 • 971 • 57 • 1 SEML-Lab/ReliableBench Viewer • Updated Mar 11 • 43 • 63 • 1 SEML-Lab/CoinflipForSafety Viewer • Updated Mar 11 • 6.56k • 82 • 1 A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness Paper • 2603.06594 • Published Feb 4 • 1
A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness Paper • 2603.06594 • Published Feb 4 • 1
IHO Attacker models of "Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs" SEML-Lab/IHO-Llama-3-8B-Instruct Updated Jun 3 • 84 SEML-Lab/IHO-CircuitBreaker-Llama-3-8B-PolyGuard Updated Jun 3 • 10 SEML-Lab/IHO-Qwen2.5-32B-Instruct Updated Jun 3 • 12 SEML-Lab/IHO-Qwen2.5-7B-Instruct-PolyGuard Updated Jun 3 • 8
