CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation

• URL: http://arxiv.org/abs/2504.13201v2
• Date: Thu, 31 Jul 2025 06:22:28 GMT
• Title: CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation
• Authors: Jirui Yang, Zheyu Lin, Zhihui Lu, Yinggui Wang, Lei Wang, Tao Wei, Xin Du, Shuhan Yang,
• Abstract summary: Large Language Models (LLMs) are increasingly becoming the cognitive core of Embodied Intelligence (EI) systems.<n>We propose a novel and efficient inference-time defense framework: Concept Enhancement Engineering (CEE)<n>CEE enhances the model's inherent safety mechanisms by directly manipulating its internal representations.
• Score: 23.07221882519171
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are increasingly becoming the cognitive core of Embodied Intelligence (EI) systems, such as robots and autonomous vehicles. However, this integration also exposes them to serious jailbreak risks, where malicious instructions can be transformed into dangerous physical actions. Existing defense mechanisms suffer from notable drawbacks--including high training costs, significant inference delays, and complex hyperparameter tuning--which limit their practical applicability. To address these challenges, we propose a novel and efficient inference-time defense framework: Concept Enhancement Engineering (CEE). CEE enhances the model's inherent safety mechanisms by directly manipulating its internal representations, requiring neither additional training nor external modules, thereby improving defense efficiency. Furthermore, CEE introduces a rotation-based control mechanism that enables stable and linearly tunable behavioral control of the model. This design eliminates the need for tedious manual tuning and avoids the output degradation issues commonly observed in other representation engineering methods. Extensive experiments across multiple EI safety benchmarks and diverse attack scenarios demonstrate that CEE significantly improves the defense success rates of various multimodal LLMs. It effectively mitigates safety risks while preserving high-quality generation and inference efficiency, offering a promising solution for deploying safer embodied intelligence systems.

Related papers

• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models [62.16655896700062]
  Activation steering is a technique to enhance the utility of Large Language Models (LLMs)<n>We show that it unintentionally introduces critical and under-explored safety risks.<n>Experiments reveal that these interventions act as a force multiplier, creating new vulnerabilities to jailbreaks and increasing attack success rates to over 80% on standard benchmarks.
  arXiv  Detail & Related papers  (2026-02-03T12:32:35Z)
• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment [43.86865924673546]
  We propose SafeThinker, an adaptive framework that allocates defensive resources via a lightweight gateway classifier.<n> Experiments show that SafeThinker significantly lowers attack success rates across diverse jailbreak strategies without compromising robustness.
  arXiv  Detail & Related papers  (2026-01-23T07:12:53Z)
• SAID: Empowering Large Language Models with Self-Activating Internal Defense [23.654016424365906]
  We introduce a new, training-free defense paradigm, Self-Activating Internal Defense (SAID)<n>SAID reframes the defense task from external correction to internal capability activation.<n>It substantially outperforms state-of-the-art defenses in reducing harmful outputs.
  arXiv  Detail & Related papers  (2025-10-23T02:07:54Z)
• UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models [67.91151588917396]
  Large Language Models (LLMs) have achieved remarkable progress across a wide range of tasks, but remain vulnerable to safety risks such as harmful content generation and jailbreak attacks.<n>We propose UpSafe$circ$C, a unified framework for enhancing LLM safety through safety-aware upcycling.<n>Our results highlight a new direction for LLM safety: moving from static alignment toward dynamic, modular, and inference-aware control.
  arXiv  Detail & Related papers  (2025-10-02T16:43:33Z)
• Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security [63.41350337821108]
  We propose Secure Tug-of-War (SecTOW) to enhance the security of multimodal large language models (MLLMs)<n>SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO)<n>We show that SecTOW significantly improves security while preserving general performance.
  arXiv  Detail & Related papers  (2025-07-29T17:39:48Z)
• Thought Purity: Defense Paradigm For Chain-of-Thought Attack [14.92561128881555]
  We propose Thought Purity, a defense paradigm that strengthens resistance to malicious content while preserving operational efficacy.<n>Our approach establishes the first comprehensive defense mechanism against CoTA vulnerabilities in reinforcement learning-aligned reasoning systems.
  arXiv  Detail & Related papers  (2025-07-16T15:09:13Z)
• Towards provable probabilistic safety for scalable embodied AI systems [79.31011047593492]
  Embodied AI systems are increasingly prevalent across various applications.<n> Ensuring their safety in complex operating environments remains a major challenge.<n>This Perspective offers a pathway toward safer, large-scale adoption of embodied AI systems in safety-critical applications.
  arXiv  Detail & Related papers  (2025-06-05T15:46:25Z)
• An Approach to Technical AGI Safety and Security [72.83728459135101]
  We develop an approach to address the risk of harms consequential enough to significantly harm humanity.<n>We focus on technical approaches to misuse and misalignment.<n>We briefly outline how these ingredients could be combined to produce safety cases for AGI systems.
  arXiv  Detail & Related papers  (2025-04-02T15:59:31Z)
• Representation Bending for Large Language Model Safety [27.842146980762934]
  Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks pose significant challenges.<n>This paper introduces RepBend, a novel approach that fundamentally disrupts the representations underlying harmful behaviors in LLMs.<n>RepBend achieves state-of-the-art performance, outperforming prior methods such as Circuit Breaker, RMU, and NPO, with up to 95% reduction in attack success rates.
  arXiv  Detail & Related papers  (2025-04-02T09:47:01Z)
• Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense [90.71884758066042]
  Large vision-language models (LVLMs) introduce a unique vulnerability: susceptibility to malicious attacks via visual inputs.<n>We propose ESIII (Embedding Security Instructions Into Images), a novel methodology for transforming the visual space from a source of vulnerability into an active defense mechanism.
  arXiv  Detail & Related papers  (2025-03-14T17:39:45Z)
• How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation [39.44000290664494]
  Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability.<n>This paper systematically examines jailbreak defenses by reframing the standard generation task as a binary classification problem.<n>We identify two key defense mechanisms: safety shift, which increases refusal rates across all queries, and harmfulness discrimination, which improves the model's ability to distinguish between harmful and benign inputs.
  arXiv  Detail & Related papers  (2025-02-20T12:07:40Z)
• Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking [26.812138599896997]
  We propose Reasoning-to-Defend (R2D), a novel training paradigm that integrates safety reflections of queries and responses into LLM's generation process.<n>R2D effectively mitigates various attacks and improves overall safety, highlighting the substantial potential of safety-aware reasoning in strengthening LLMs' robustness against jailbreaks.
  arXiv  Detail & Related papers  (2025-02-18T15:48:46Z)
• Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks [25.212057612342218]
  Large language models (LLMs) are susceptible to jailbreak attacks, which exploit system vulnerabilities to bypass safety measures and generate harmful outputs.<n>We propose a Latent-space Adversarial Training with Post-aware framework to address this problem.
  arXiv  Detail & Related papers  (2025-01-18T02:57:12Z)
• In-Context Experience Replay Facilitates Safety Red-Teaming of Text-to-Image Diffusion Models [104.94706600050557]
  Text-to-image (T2I) models have shown remarkable progress, but their potential to generate harmful content remains a critical concern in the ML community.<n>We propose ICER, a novel red-teaming framework that generates interpretable and semantic meaningful problematic prompts.<n>Our work provides crucial insights for developing more robust safety mechanisms in T2I systems.
  arXiv  Detail & Related papers  (2024-11-25T04:17:24Z)
• Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics [68.36528819227641]
  This paper systematically quantifies the robustness of VLA-based robotic systems.<n>We introduce two untargeted attack objectives that leverage spatial foundations to destabilize robotic actions, and a targeted attack objective that manipulates the robotic trajectory.<n>We design an adversarial patch generation approach that places a small, colorful patch within the camera's view, effectively executing the attack in both digital and physical environments.
  arXiv  Detail & Related papers  (2024-11-18T01:52:20Z)
• Defining and Evaluating Physical Safety for Large Language Models [62.4971588282174]
  Large Language Models (LLMs) are increasingly used to control robotic systems such as drones. Their risks of causing physical threats and harm in real-world applications remain unexplored. We classify the physical safety risks of drones into four categories: (1) human-targeted threats, (2) object-targeted threats, (3) infrastructure attacks, and (4) regulatory violations.
  arXiv  Detail & Related papers  (2024-11-04T17:41:25Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)
• Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems [27.316115171846953]
  Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied AI. LLMs are fine-tuned to leverage their inherent common sense and reasoning abilities while being tailored to specific applications. This fine-tuning process introduces considerable safety and security vulnerabilities, especially in safety-critical cyber-physical systems.
  arXiv  Detail & Related papers  (2024-05-27T17:59:43Z)
• Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications [58.06882713631082]
  Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks raises serious security concerns. This paper proposes an efficient attention-based defense mechanism that exploits adversarial channel-attention to quickly identify and track malicious objects in shallow network layers. It also introduces an efficient multi-frame defense framework, validating its efficacy through extensive experiments aimed at evaluating both defense performance and computational cost.
  arXiv  Detail & Related papers  (2023-11-19T00:47:17Z)

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.