ATTCK-R: Knowledge-Aware Long-Horizon Jailbreaking for Protected LLMs
As large language models are deployed behind increasingly sophisticated safety mechanisms, evaluating their robustness under realistic adversarial conditions becomes increasingly difficult and critical. Existing jailbreaking evaluations often rely on static prompts, limited interaction horizons, or lightly protected systems, failing to reflect protected deployment settings with prompt-based safety protections. We show that the introduction of a prompt-based safety protection reduces the average attack success rate of a strong multi-turn baseline from 0.896 to 0.608 (32.1\% relative), demonstrating that unprotected evaluations substantially overestimate real-world vulnerabilities. We propo...
| Authors | Md Mushfiqur Rahman, Tobias Rohde, Rahul Tripathi et al. |
|---|---|
| Primary category | cs.CR |
| Published | 12 October 2026 |
| Last updated at source | 12 October 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.