SafeDream: Safety World Model for Proactive Early Jailbreak Detection
Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art models. Existing alignment-based and guardrail methods suffer from three key limitations: they require costly weight modification, evaluate each turn independently without modeling cumulative safety erosion, and detect attacks only after harmful content has been generated. To address these limitations, we first formulate the proactive early jailbreak detection problem with a new metric, detection lead, that measures how early an attack can be detected before the LLM complies. We then propose SAFEDREAM, a lightweight world-model-based framework that operates as an external module without modifying the LLM's weights. SAFEDREAM introduces three components: (1) a safety state world model that encodes LLM hidden states into a compact safety representation and predicts how it evolves across turns, (2) CUSUM detection that accumulates weak per-turn risk signals into reliable evidence, and (3) contrastive imagination that simultaneously rolls out attack and benign futures in latent space to issue early alarms before jailbreaks occur. On three multi-turn jailbreak benchmarks (XGuard-Train, SafeDialBench, SafeMTData) against 8 baselines, SAFEDREAM achieves the best detection timeliness across all benchmarks (1.06-1.20 turns before compliance) while maintaining competitive false positive rates and outperforming baselines in detection quality.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SafeDreamer: Safe Reinforcement Learning with World Models
The deployment of Reinforcement Learning (RL) in real-world applications is constrained by its failure to satisfy safety criteria. Existing Safe Reinforcement Learning (SafeRL) methods, which rely on cost functions to en…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement LearningProactive defense against LLM Jailbreak
The proliferation of powerful large language models (LLMs) has necessitated robust safety alignment, yet these models remain vulnerable to evolving adversarial attacks, including multi-turn jailbreaks that iteratively se…
Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
Large language models (LLMs) are highly vulnerable to jailbreaking attacks, wherein adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detect…
Safety AlignmentEnhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal a…
BlockingSafety AlignmentActive Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreaks
Large language models (LLMs) are increasingly vulnerable to multi-turn jailbreak attacks, where adversaries iteratively elicit harmful behaviors that bypass single-turn safety filters. Existing defenses predominantly rel…