SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915999487361024 |
|---|---|
| author | Chen, Yulong Zhang, Qi Zhang, Jiawen Liu, Yadong Li, Mu Wen, Jie Xu, Yong |
| author_facet | Chen, Yulong Zhang, Qi Zhang, Jiawen Liu, Yadong Li, Mu Wen, Jie Xu, Yong |
| contents | Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering, auxiliary guardrails, or decoding-time control. However, these interventions often reduce practical deployability because they may require additional model access, introduce extra inference cost, or affect benign-task utility. In this paper, we propose Safety-Aware Intent Defense (SAID), a training-free jailbreak defense framework based on intent-level safety probing. SAID first distills potentially obfuscated user inputs into concise core intents using the target model itself. It then applies a validated safety prefix to probe each distilled intent and elicit the model's safety-aware response. Finally, a conservative aggregation rule rejects the original request if any distilled intent is identified as unsafe. This design enables black-box-compatible defense without updating model parameters or modifying the decoding process. Experiments on four open-source LLMs under six representative jailbreak attacks show that SAID achieves state-of-the-art defense performance in reducing harmful responses while maintaining competitive utility on benign tasks. Further analyses on prefix variants, hierarchical distillation, and inference efficiency demonstrate that SAID provides a practical safety-utility trade-off for securing LLMs against jailbreak threats. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20129 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models Chen, Yulong Zhang, Qi Zhang, Jiawen Liu, Yadong Li, Mu Wen, Jie Xu, Yong Cryptography and Security Artificial Intelligence Large Language Models (LLMs) remain vulnerable to jailbreak attacks, where adversarially crafted prompts induce policy-violating responses despite safety alignment. Existing defenses typically improve safety through external filtering, auxiliary guardrails, or decoding-time control. However, these interventions often reduce practical deployability because they may require additional model access, introduce extra inference cost, or affect benign-task utility. In this paper, we propose Safety-Aware Intent Defense (SAID), a training-free jailbreak defense framework based on intent-level safety probing. SAID first distills potentially obfuscated user inputs into concise core intents using the target model itself. It then applies a validated safety prefix to probe each distilled intent and elicit the model's safety-aware response. Finally, a conservative aggregation rule rejects the original request if any distilled intent is identified as unsafe. This design enables black-box-compatible defense without updating model parameters or modifying the decoding process. Experiments on four open-source LLMs under six representative jailbreak attacks show that SAID achieves state-of-the-art defense performance in reducing harmful responses while maintaining competitive utility on benign tasks. Further analyses on prefix variants, hierarchical distillation, and inference efficiency demonstrate that SAID provides a practical safety-utility trade-off for securing LLMs against jailbreak threats. |
| title | SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2510.20129 |