Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.29629 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913169975279616 |
|---|---|
| author | Park, Junyoung Park, Sunghwan Ju, Seongyong Lee, Jaewoo |
| author_facet | Park, Junyoung Park, Sunghwan Ju, Seongyong Lee, Jaewoo |
| contents | Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not how it unfolded. Two attacks that produce equally harmful outputs may have followed completely different paths, and ASR cannot tell them apart. We make those hidden paths observable from logits alone. Temporal Logit Observability (TLO) is a training-free diagnostic that watches a compliance-refusal margin during decoding and places each model-attack condition on a calibrated 2D plane. By design, this plane is most informative exactly where ASR is least informative: among attacks that succeed for genuinely different reasons. Across four aligned LLMs and three jailbreak paradigms, attacks with nearly identical ASR land at clearly different points on the plane: the same model can fail through different temporal patterns. The geometry matches refusal-direction probes from hidden states on most conditions, with one model showing the limit of our fixed-lexicon approach. A simple early-stop rule derived from TLO cuts successful jailbreaks by more than half, without false alarms on plain benign queries. Safety evaluation should report when and how a failure unfolds, not only whether it occurred. TLO makes the first two observable from logits alone. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29629 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures Park, Junyoung Park, Sunghwan Ju, Seongyong Lee, Jaewoo Artificial Intelligence Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation, telling us whether a failure happened but not how it unfolded. Two attacks that produce equally harmful outputs may have followed completely different paths, and ASR cannot tell them apart. We make those hidden paths observable from logits alone. Temporal Logit Observability (TLO) is a training-free diagnostic that watches a compliance-refusal margin during decoding and places each model-attack condition on a calibrated 2D plane. By design, this plane is most informative exactly where ASR is least informative: among attacks that succeed for genuinely different reasons. Across four aligned LLMs and three jailbreak paradigms, attacks with nearly identical ASR land at clearly different points on the plane: the same model can fail through different temporal patterns. The geometry matches refusal-direction probes from hidden states on most conditions, with one model showing the limit of our fixed-lexicon approach. A simple early-stop rule derived from TLO cuts successful jailbreaks by more than half, without false alarms on plain benign queries. Safety evaluation should report when and how a failure unfolds, not only whether it occurred. TLO makes the first two observable from logits alone. |
| title | Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.29629 |