Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
- URL: http://arxiv.org/abs/2501.02029v1
- Date: Fri, 03 Jan 2025 07:01:15 GMT
- Title: Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models
- Authors: Ziwei Zheng, Junyao Zhao, Le Yang, Lijun He, Fan Li,
- Abstract summary: Internal activations of large vision-language models (LVLMs) can identify malicious prompts across different attacks.<n>This inherent safety perception is governed by sparse attention heads, which we term safety heads"<n>By locating these safety heads and concatenating their activations, we construct a straightforward but powerful malicious prompt detector.
- Score: 9.318094073527563
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted considerable effort to the post-hoc alignment of LVLMs, the inner safety mechanisms remain largely unexplored. In this paper, we discover that internal activations of LVLMs during the first token generation can effectively identify malicious prompts across different attacks. This inherent safety perception is governed by sparse attention heads, which we term ``safety heads." Further analysis reveals that these heads act as specialized shields against malicious prompts; ablating them leads to higher attack success rates, while the model's utility remains unaffected. By locating these safety heads and concatenating their activations, we construct a straightforward but powerful malicious prompt detector that integrates seamlessly into the generation process with minimal extra inference overhead. Despite its simple structure of a logistic regression model, the detector surprisingly exhibits strong zero-shot generalization capabilities. Experiments across various prompt-based attacks confirm the effectiveness of leveraging safety heads to protect LVLMs. Code is available at \url{https://github.com/Ziwei-Zheng/SAHs}.
Related papers
- The Safety Reminder: A Soft Prompt to Reactivate Delayed Safety Awareness in Vision-Language Models [4.27794555931853]
Vision-Language Models (VLMs) face unique vulnerabilities due to their multimodal nature, allowing adversaries to bypass safety guardrails and trigger the generation of harmful content.<n>We propose The Safety Reminder'', a soft prompt tuning approach that optimize learnable prompt tokens, which are periodically injected during the text generation process to enhance safety awareness.
arXiv Detail & Related papers (2025-06-15T12:48:38Z) - SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning [76.56522719330911]
Large Reasoning Models (LRMs) introduce a new generation paradigm of explicitly reasoning before answering.<n>LRMs pose great safety risks against harmful queries and adversarial attacks.<n>We propose SafeKey to better activate the safety aha moment in the key sentence.
arXiv Detail & Related papers (2025-05-22T03:46:03Z) - One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models [20.42976162135529]
Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research.<n>We propose textttD-STT, a simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens of the given safety-aligned LLM.
arXiv Detail & Related papers (2025-05-12T01:26:50Z) - 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) - Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking [15.953888359667497]
jailbreak attacks based on prompt engineering have become a major safety threat.<n>This study introduces the concept of Defense Threshold Decay (DTD), revealing the potential safety impact caused by LLMs' benign generation.<n>We propose the Sugar-Coated Poison attack paradigm, which uses a "semantic reversal" strategy to craft benign inputs that are opposite in meaning to malicious intent.
arXiv Detail & Related papers (2025-04-08T03:57:09Z) - Exposing the Ghost in the Transformer: Abnormal Detection for Large Language Models via Hidden State Forensics [5.384257830522198]
Large Language Models (LLMs) in critical applications have introduced severe reliability and security risks.
These vulnerabilities have been weaponized by malicious actors, leading to unauthorized access, widespread misinformation, and compromised system integrity.
We introduce a novel approach to detecting abnormal behaviors in LLMs via hidden state forensics.
arXiv Detail & Related papers (2025-04-01T05:58:14Z) - 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.
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) - 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.
Our findings reveal that LVLMs exhibit distinct activation patterns when processing unsafe prompts.
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) - Internal Activation as the Polar Star for Steering Unsafe LLM Behavior [50.463399903987245]
We introduce SafeSwitch, a framework that dynamically regulates unsafe outputs by monitoring and utilizing the model's internal states.
Our empirical results show that SafeSwitch reduces harmful outputs by over 80% on safety benchmarks while maintaining strong utility.
arXiv Detail & Related papers (2025-02-03T04:23:33Z) - Targeting the Core: A Simple and Effective Method to Attack RAG-based Agents via Direct LLM Manipulation [4.241100280846233]
AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication.<n>This paper investigates a critical vulnerability: adversarial attacks targeting the LLM core within AI agents.
arXiv Detail & Related papers (2024-12-05T18:38:30Z) - SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering [56.92068213969036]
Safety alignment is indispensable for Large Language Models (LLMs) to defend threats from malicious instructions.<n>Recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue.<n>We propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns.
arXiv Detail & Related papers (2024-08-21T10:01:34Z) - SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance [48.36220909956064]
SafeAligner is a methodology implemented at the decoding stage to fortify defenses against jailbreak attacks.<n>We develop two specialized models: the Sentinel Model, which is trained to foster safety, and the Intruder Model, designed to generate riskier responses.<n>We show that SafeAligner can increase the likelihood of beneficial tokens, while reducing the occurrence of harmful ones.
arXiv Detail & Related papers (2024-06-26T07:15:44Z) - 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) - Uncovering Safety Risks of Large Language Models through Concept Activation Vector [13.804245297233454]
We introduce a Safety Concept Activation Vector (SCAV) framework to guide attacks on large language models (LLMs)<n>We then develop an SCAV-guided attack method that can generate both attack prompts and embedding-level attacks.<n>Our attack method significantly improves the attack success rate and response quality while requiring less training data.
arXiv Detail & Related papers (2024-04-18T09:46:25Z) - Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models [79.0183835295533]
We introduce the first benchmark for indirect prompt injection attacks, named BIPIA, to assess the risk of such vulnerabilities.
Our analysis identifies two key factors contributing to their success: LLMs' inability to distinguish between informational context and actionable instructions, and their lack of awareness in avoiding the execution of instructions within external content.
We propose two novel defense mechanisms-boundary awareness and explicit reminder-to address these vulnerabilities in both black-box and white-box settings.
arXiv Detail & Related papers (2023-12-21T01:08:39Z) - Visual Adversarial Examples Jailbreak Aligned Large Language Models [66.53468356460365]
We show that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks.
We exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision.
Our study underscores the escalating adversarial risks associated with the pursuit of multimodality.
arXiv Detail & Related papers (2023-06-22T22:13:03Z)
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.