Measuring the Wrong Thing: Internal Harmfulness Scores Anti-Rank Successful Jailbreaks
Internal safety scores judge a prompt before any text is generated, and they are validated by how well they separate harmful prompts from benign ones. That separation is then read as evidence that the score will also catch the attacks that succeed. Harmful intent is a property of the prompt. Jailbreak success is an outcome produced later by a particular target model, decoding policy, and judge. A filter tuned on a score that measures the wrong quantity spends its false positive budget on attacks that would have failed anyway. In this paper we audit that inference. Attention based measurements are usually read from prompt dependent locations, so a wrapper changes both the content being jud...
| Authors | Mingyu Luo, Ming Deng, Zilang Qiu et al. |
|---|---|
| Primary category | cs.CL |
| Published | 10 August 2026 |
| Last updated at source | 10 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.