The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections · HackerPapers discussions

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections — HN submission

Mon, 17 Nov 2025 12:09:37 GMT

Attacker Moves Second: Adaptive Attacks Bypass Defenses Against LLM Jailbreaks

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections — HN submission

Sun, 16 Nov 2025 17:25:20 GMT

Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections — mentioned by jnwatson

Sun, 16 Nov 2025 17:03:28 GMT

There's a big gap of knowledge between infosec researchers and ML security researchers. Anthropic has a bunch of column B but not enough column A. This was discussed in some detail in the recently published Attacker Moves Second paper*. ML researchers like using Attack Success Rate (ASR) as a metric for model resistance to attack, while for infosec, any successful attack (ASR > 0) is considered significant. ML researchers generally use a static set of tests, while infosec researchers assume an adaptive, resourceful attacker. • https://arxiv.org/abs/2510.09023

Paper and discussion history. A mention is not an endorsement.

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections — HN submission

Mon, 13 Oct 2025 21:16:06 GMT

Stronger Adaptive Attacks Bypass Defenses Against LLM Jailbreaks

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.