Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States

• URL: http://arxiv.org/abs/2503.09066v2
• Date: Fri, 04 Jul 2025 15:13:55 GMT
• Title: Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks.<n>Yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks.<n>We investigated the underlying latent subspaces of safe and jailbroken states by extracting hidden activations from a LLM.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms to generate restricted or harmful content. In this study, we investigated the underlying latent subspaces of safe and jailbroken states by extracting hidden activations from a LLM. Inspired by attractor dynamics in neuroscience, we hypothesized that LLM activations settle into semi stable states that can be identified and perturbed to induce state transitions. Using dimensionality reduction techniques, we projected activations from safe and jailbroken responses to reveal latent subspaces in lower dimensional spaces. We then derived a perturbation vector that when applied to safe representations, shifted the model towards a jailbreak state. Our results demonstrate that this causal intervention results in statistically significant jailbreak responses in a subset of prompts. Next, we probed how these perturbations propagate through the model's layers, testing whether the induced state change remains localized or cascades throughout the network. Our findings indicate that targeted perturbations induced distinct shifts in activations and model responses. Our approach paves the way for potential proactive defenses, shifting from traditional guardrail based methods to preemptive, model agnostic techniques that neutralize adversarial states at the representation level.

Related papers

• SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense [77.70598852234149]
  Text-to-Video (T2V) generative models are vulnerable to jailbreak attacks in real-world deployment.<n>We propose SafeCA, a feature-level defense mechanism for safe cross-attention localization and regularization.<n> Experimental results show that SafeCA reduces the jailbreak success rate by about 20% on mainstream T2V models.
  arXiv  Detail & Related papers  (2026-08-11T14:01:24Z)
• ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety [54.4092272526747]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities.<n>We propose ProjLens, an interpretability framework designed to demystify MLLMs backdoors.
  arXiv  Detail & Related papers  (2026-04-21T04:52:38Z)
• Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models [71.11171576590134]
  Vision-language models can be easily induced by visual jailbreak attacks to generate harmful content.<n>We propose NullSteer, a null-space projected activation defense framework.<n>We show that NullSteer significantly reduces harmful outputs under various jailbreak attacks.
  arXiv  Detail & Related papers  (2026-03-23T15:23:23Z)
• Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt [1.6916040234975798]
  We present a jailbreak technique for Large Language Models (LLMs)<n>We manipulate the model's internal activations to alter its generation trajectory without changing the prompt.<n>We show that this activation surgery method reveals where and how refusal arises, and prevents refusal signals from propagating across layers.
  arXiv  Detail & Related papers  (2026-03-15T08:24:38Z)
• 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)
• A Fragile Guardrail: Diffusion LLM's Safety Blessing and Its Failure Mode [51.43498132808724]
  We show that Diffusion large language models (D-LLMs) have intrinsic robustness against jailbreak attacks.<n>We identify a simple yet effective failure mode, termed context nesting, where harmful requests are embedded within structured benign contexts.<n>We show that this simple strategy is sufficient to bypass D-LLMs' safety blessing, achieving state-of-the-art attack success rates.
  arXiv  Detail & Related papers  (2026-01-30T23:08:14Z)
• 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)
• Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift [23.0914017433021]
  This work identifies a novel class of deployment phase attacks that exploit a vulnerability by injecting imperceptible perturbations directly into the embedding layer outputs without modifying model weights or input text.<n>We propose Search based Embedding Poisoning, a practical, model agnostic framework that introduces carefully optimized perturbations into embeddings associated with high risk tokens.
  arXiv  Detail & Related papers  (2025-09-08T05:00:58Z)
• Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers [0.0]
  Large language models (LLMs) aligned for safety often exhibit emergent deceptive behaviors.<n>This paper introduces adversarial activation patching, a novel mechanistic interpretability framework.<n>By sourcing activations from "deceptive" prompts, we simulate vulnerabilities and quantify deception rates.
  arXiv  Detail & Related papers  (2025-07-12T21:29:49Z)
• Probing the Robustness of Large Language Models Safety to Latent Perturbations [30.16804362984161]
  Safety alignment is a key requirement for building reliable Artificial General Intelligence.<n>We observe that minor latent shifts can still trigger unsafe responses in aligned models.<n>We introduce Layer-wise Adversarial Patch Training(LAPT), a fine-tuning strategy that injects controlled perturbations into hidden representations during training.
  arXiv  Detail & Related papers  (2025-06-19T07:03:05Z)
• Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement [48.50995874445193]
  Large Language Models (LLMs) have shown impressive capabilities across various tasks but remain vulnerable to meticulously crafted jailbreak attacks.<n>We propose SAGE (Self-Aware Guard Enhancement), a training-free defense strategy designed to align LLMs' strong safety discrimination performance with their relatively weaker safety generation ability.
  arXiv  Detail & Related papers  (2025-05-17T15:54:52Z)
• Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs [83.11815479874447]
  We propose a novel jailbreak attack framework, inspired by cognitive decomposition and biases in human cognition.<n>We employ cognitive decomposition to reduce the complexity of malicious prompts and relevance bias to reorganize prompts.<n>We also introduce a ranking-based harmfulness evaluation metric that surpasses the traditional binary success-or-failure paradigm.
  arXiv  Detail & Related papers  (2025-05-03T05:28:11Z)
• Feature-Aware Malicious Output Detection and Mitigation [8.378272216429954]
  We propose a feature-aware method for harmful response rejection (FMM) FMM detects the presence of malicious features within the model's feature space and adaptively adjusts the model's rejection mechanism. Experimental results demonstrate the effectiveness of our approach across multiple language models and diverse attack techniques.
  arXiv  Detail & Related papers  (2025-04-12T12:12:51Z)
• Improving LLM Safety Alignment with Dual-Objective Optimization [65.41451412400609]
  Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. We propose an improved safety alignment that disentangles DPO objectives into two components: (1) robust refusal training, which encourages refusal even when partial unsafe generations are produced, and (2) targeted unlearning of harmful knowledge.
  arXiv  Detail & Related papers  (2025-03-05T18:01:05Z)
• Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks [55.29301192316118]
  Large language models (LLMs) are highly vulnerable to jailbreaking attacks.<n>We propose a safety steering framework grounded in safe control theory.<n>Our method achieves invariant safety at each turn of dialogue by learning a safety predictor.
  arXiv  Detail & Related papers  (2025-02-28T21:10:03Z)
• HiddenDetect: Detecting Jailbreak Attacks against Large Vision-Language Models via Monitoring Hidden States [17.601328965546617]
  We investigate whether LVLMs inherently encode safety-relevant signals within their internal activations during inference.<n>Our findings reveal that LVLMs exhibit distinct activation patterns when processing unsafe prompts.<n>We introduce HiddenDetect, a novel tuning-free framework that harnesses internal model activations to enhance safety.
  arXiv  Detail & Related papers  (2025-02-20T17:14:34Z)
• 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)
• Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models [59.25318174362368]
  Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text.<n>We conduct a detailed analysis of seven different jailbreak methods and find that disagreements stem from insufficient observation samples.<n>We propose a novel defense called textbfActivation Boundary Defense (ABD), which adaptively constrains the activations within the safety boundary.
  arXiv  Detail & Related papers  (2024-12-22T14:18:39Z)
• LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts [88.96201324719205]
  Safety concerns in large language models (LLMs) have gained significant attention due to their exposure to potentially harmful data during pre-training.<n>We identify a new safety vulnerability in LLMs, where seemingly benign prompts, semantically related to harmful content, can bypass safety mechanisms.<n>We introduce a novel attack method, textitActorBreaker, which identifies actors related to toxic prompts within pre-training distribution.
  arXiv  Detail & Related papers  (2024-10-14T16:41:49Z)
• Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models [8.024771725860127]
  Jailbreak attacks manipulate large language models into generating harmful content. Jailbreak Antidote enables real-time adjustment of safety preferences by manipulating a sparse subset of the model's internal states. Our analysis reveals that safety-related information in LLMs is sparsely distributed.
  arXiv  Detail & Related papers  (2024-10-03T08:34:17Z)
• Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space [0.24578723416255752]
  This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies. It proposes a novel method for their detection at runtime.
  arXiv  Detail & Related papers  (2024-07-21T13:48:23Z)
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models [57.5404308854535]
  Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.
  arXiv  Detail & Related papers  (2024-06-24T19:29:47Z)
• Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons [57.07507194465299]
  Large language models (LLMs) excel in various capabilities but pose safety risks such as generating harmful content and misinformation, even after safety alignment.<n>We focus on identifying and analyzing safety neurons within LLMs that are responsible for safety behaviors.<n>We propose inference-time activation contrasting to locate these neurons and dynamic activation patching to evaluate their causal effects on model safety.
  arXiv  Detail & Related papers  (2024-06-20T09:35:22Z)
• Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable [70.77600345240867]
  A novel arbitrary-in-arbitrary-out (AIAO) strategy makes watermarks resilient to fine-tuning-based removal. Unlike the existing methods of designing a backdoor for the input/output space of diffusion models, in our method, we propose to embed the backdoor into the feature space of sampled subpaths. Our empirical studies on the MS-COCO, AFHQ, LSUN, CUB-200, and DreamBooth datasets confirm the robustness of AIAO.
  arXiv  Detail & Related papers  (2024-05-01T12:03:39Z)
• Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective [43.94115802328438]
  Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs.<n>We suggest that the self-safeguarding capability of LLMs is linked to specific activity patterns within their representation space.<n>Our findings demonstrate that these patterns can be detected with just a few pairs of contrastive queries.
  arXiv  Detail & Related papers  (2024-01-12T00:50:04Z)
• Weakly Supervised Representation Learning with Sparse Perturbations [82.39171485023276]
  We show that if one has weak supervision from observations generated by sparse perturbations of the latent variables, identification is achievable under unknown continuous latent distributions. We propose a natural estimation procedure based on this theory and illustrate it on low-dimensional synthetic and image-based experiments.
  arXiv  Detail & Related papers  (2022-06-02T15:30:07Z)

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.