LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems

LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems arXiv:2606.20408v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as operators of a safety…

https://arxiv.org/abs/2606.20408

sha256:a0f0772628ed72abf60a39ef51501909fe503bb5e2b7fd7ed9bce3eff4c6594b

• cve0
• md50
• url0
• ipv40
• ipv60
• sha10
• domain0
• sha2560
• malware_token0
• attack_pattern0
• threat_actor_token0