TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense

• URL: http://arxiv.org/abs/2604.07727v1
• Date: Thu, 09 Apr 2026 02:22:44 GMT
• Title: TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense
• Abstract summary: Existing jailbreak defense paradigms rely on static detection of prompts, outputs, or internal states.<n>We show that hidden states in critical layers during decoding carry stronger and more stable risk signals than input jailbreak prompts.<n>We propose TrajGuard, a training-free, decoding-time defense framework.
• Score: 22.678364306206493
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic evolution of risk during decoding. This oversight leaves risk signals embedded in decoding trajectories underutilized, constituting a critical blind spot in current defense systems. In this work, we empirically demonstrate that hidden states in critical layers during the decoding phase carry stronger and more stable risk signals than input jailbreak prompts. Specifically, the hidden representations of tokens generated during jailbreak attempts progressively approach high-risk regions in the latent space. Based on this observation, we propose TrajGuard, a training-free, decoding-time defense framework. TrajGuard aggregates hidden-state trajectories via a sliding window to quantify risk in real time, triggering a lightweight semantic adjudication only when risk within a local window persistently exceeds a threshold. This mechanism enables the immediate interruption or constraint of subsequent decoding. Extensive experiments across 12 jailbreak attacks and various open-source LLMs show that TrajGuard achieves an average defense rate of 95%. Furthermore, it reduces detection latency to 5.2 ms/token while maintaining a false positive rate below 1.5%. These results confirm that hidden-state trajectories during decoding can effectively support real-time jailbreak detection, highlighting a promising direction for defenses without model modification.

Related papers

• SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement [27.972348333797385]
  We propose a unified detection framework for large language models (LLMs)<n>Our method is grounded in a paramount observation: high fluency prompts maintain their malicious intention close to harmful prompts.<n>Our evaluation demonstrates that SAFEGuard consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-09-05T03:25:31Z)
• Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics [50.36375380196006]
  Jailbreak prompts can bypass alignment guardrails in large language models.<n>Prior detection approaches largely rely on a fixed metric space.<n>We show this assumption breaks under (i) pseudo-malicious prompts that are benign by intent but contain safety-related keywords.<n>We present Manifold Trajectory Kinetics (MTK), which treats an LLM as a kinetic system transforming inputs into outputs.
  arXiv  Detail & Related papers  (2026-06-05T14:49:26Z)
• Jailbreaking Leaves a Trace: Understanding and Detecting Jailbreak Attacks from Internal Representations of Large Language Models [2.6140509675507384]
  We study jailbreaking from both security and interpretability perspectives.<n>We propose a tensor-based latent representation framework that captures structure in hidden activations.<n>Our results provide evidence that jailbreak behavior is rooted in identifiable internal structures.
  arXiv  Detail & Related papers  (2026-02-12T02:43:17Z)
• Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing [27.582748494845706]
  Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications.<n>Despite extensive safety alignment efforts, recent studies show that such alignment is often shallow and remains vulnerable to jailbreak attacks.<n>We make a key observation: even when successfully jailbroken, models internally exhibit latent safety-related signals during generation.<n>We propose a simple yet effective approach that explicitly surfaces and leverages these latent safety signals for early detection of unsafe content during decoding.
  arXiv  Detail & Related papers  (2026-01-15T16:09:10Z)
• ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification [47.135407245022115]
  Existing detection methods mainly detect jailbreak status relying on jailbreak templates present in the training data.<n>We propose a layer-wise, module-wise, and token-wise amplification framework that progressively magnifies internal feature discrepancies between benign and jailbreak prompts.<n>Building upon these insights, we introduce ALERT, an efficient and effective zero-shot jailbreak detector.
  arXiv  Detail & Related papers  (2026-01-07T05:30:53Z)
• Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring [13.497048408038935]
  Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks.<n>Current anomaly-detection methods tend to confuse novel benign inputs with malicious ones, leading to unreliable over-rejection.<n>We propose Representational Contrastive Scoring (RCS), a framework built on a key insight: the most potent safety signals reside within the LVLM's own internal representations.
  arXiv  Detail & Related papers  (2025-12-12T22:31:38Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models [50.21378052667732]
  We conduct an in-depth analysis of dLLM vulnerabilities to jailbreak attacks across two distinct dimensions: intra-step and inter-step dynamics.<n>We propose DiffuGuard, a training-free defense framework that addresses vulnerabilities through a dual-stage approach.
  arXiv  Detail & Related papers  (2025-09-29T05:17:10Z)
• Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models [80.66766532477973]
  Test-time IMmunization (TIM) can adaptively defend against various jailbreak attacks in a self-evolving way.<n>Test-time IMmunization (TIM) can adaptively defend against various jailbreak attacks in a self-evolving way.
  arXiv  Detail & Related papers  (2025-05-28T11:57:46Z)
• Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense [55.77152277982117]
  We introduce Layer-AdvPatcher, a methodology designed to defend against jailbreak attacks.<n>We use an unlearning strategy to patch specific layers within large language models through self-augmented datasets.<n>Our framework reduces the harmfulness and attack success rate of jailbreak attacks.
  arXiv  Detail & Related papers  (2025-01-05T19:06:03Z)
• MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks [2.873719680183099]
  This paper advocates for the significance of jailbreak attack prevention on Large Language Models (LLMs) We introduce MoJE, a novel guardrail architecture designed to surpass current limitations in existing state-of-the-art guardrails. MoJE excels in detecting jailbreak attacks while maintaining minimal computational overhead during model inference.
  arXiv  Detail & Related papers  (2024-09-26T10:12:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.