The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?

• URL: http://arxiv.org/abs/2410.01438v2
• Date: Sun, 02 Feb 2025 04:59:41 GMT
• Title: The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?
• Authors: Ching-Chia Kao, Chia-Mu Yu, Chun-Shien Lu, Chu-Song Chen,
• Abstract summary: Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks.<n>We provide an information-theoretic framework for understanding the fundamental trade-off between the effectiveness of these attacks and their stealthiness.<n>We propose an efficient algorithm for detecting non-stealthy jailbreak attacks, offering significant improvements in model robustness.
• Score: 23.347349690954452
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) have achieved remarkable performance on a variety of tasks, yet they remain vulnerable to jailbreak attacks that compromise safety and reliability. In this paper, we provide an information-theoretic framework for understanding the fundamental trade-off between the effectiveness of these attacks and their stealthiness. Drawing on Fano's inequality, we demonstrate how an attacker's success probability is intrinsically linked to the stealthiness of generated prompts. Building on this, we propose an efficient algorithm for detecting non-stealthy jailbreak attacks, offering significant improvements in model robustness. Experimental results highlight the tension between strong attacks and their detectability, providing insights into both adversarial strategies and defense mechanisms.

Related papers

• 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)
• CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models [16.5022773312661]
  We propose a universal certified defence framework to safeguard large vision-language models against jailbreak attacks. First, we proposed a novel distance metric to quantify semantic discrepancies between malicious and intended responses. Then, we devise a regressed certification approach that employs randomized smoothing to provide formal robustness guarantees.
  arXiv  Detail & Related papers  (2025-03-08T17:33:55Z)
• Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis [3.795071937009966]
  Adrial attacks can jeopardize the integrity of Machine Learning (ML) models. We propose a framework that detects if an adversarial noise instance is being generated. We evaluate our approach against 8 state-of-the-art attacks, including adaptive attacks.
  arXiv  Detail & Related papers  (2025-03-04T20:25:12Z)
• 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. This paper systematically examines jailbreak defenses by reframing the standard generation task as a binary classification problem. 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)
• Turning Logic Against Itself : Probing Model Defenses Through Contrastive Questions [51.51850981481236]
  We introduce POATE, a novel jailbreak technique that harnesses contrastive reasoning to provoke unethical responses. PoATE crafts semantically opposing intents and integrates them with adversarial templates, steering models toward harmful outputs with remarkable subtlety. To counter this, we propose Intent-Aware CoT and Reverse Thinking CoT, which decompose queries to detect malicious intent and reason in reverse to evaluate and reject harmful responses.
  arXiv  Detail & Related papers  (2025-01-03T15:40:03Z)
• Antelope: Potent and Concealed Jailbreak Attack Strategy [7.970002819722513]
  Antelope is a more robust and covert jailbreak attack strategy designed to expose security vulnerabilities inherent in generative models. We successfully exploit the transferability of model-based attacks to penetrate online black-box services.
  arXiv  Detail & Related papers  (2024-12-11T07:22:51Z)
• Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks [34.40254709148148]
  Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding. Their potential safety and robustness issues raise concerns that adversaries may evade the system and cause these models to generate toxic content through malicious attacks. We present Chain of Attack (CoA), which iteratively enhances the generation of adversarial examples based on the multi-modal semantic update.
  arXiv  Detail & Related papers  (2024-11-24T05:28:07Z)
• Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey [50.031628043029244]
  Multimodal generative models are susceptible to jailbreak attacks, which can bypass built-in safety mechanisms and induce the production of potentially harmful content. This survey reviews jailbreak and defense in multimodal generative models.
  arXiv  Detail & Related papers  (2024-11-14T07:51:51Z)
• The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense [56.32083100401117]
  The vulnerability of Vision Large Language Models (VLLMs) to jailbreak attacks appears as no surprise. Recent defense mechanisms against these attacks have reached near-saturation performance on benchmark evaluations.
  arXiv  Detail & Related papers  (2024-11-13T07:57:19Z)
• HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignment [1.8843687952462742]
  This paper aims to address gaps in the current literature on jailbreaking techniques and the evaluation of LLM vulnerabilities. Our contributions include the creation of a novel dataset designed to assess the harmfulness of model outputs across multiple harm levels. We provide a comprehensive benchmark of state-of-the-art jailbreaking attacks, specifically targeting the Vicuna 13B v1.5 model.
  arXiv  Detail & Related papers  (2024-11-11T10:02:49Z)
• Jailbreaking and Mitigation of Vulnerabilities in Large Language Models [4.564507064383306]
  Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation. Despite these advancements, LLMs have shown considerable vulnerabilities, particularly to prompt injection and jailbreaking attacks. This review analyzes the state of research on these vulnerabilities and presents available defense strategies.
  arXiv  Detail & Related papers  (2024-10-20T00:00:56Z)
• BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models [47.576957746503666]
  BlackDAN is an innovative black-box attack framework with multi-objective optimization. It generates high-quality prompts that effectively facilitate jailbreaking. It maintains contextual relevance and minimize detectability.
  arXiv  Detail & Related papers  (2024-10-13T11:15:38Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing [107.97160023681184]
  Aligned large language models (LLMs) are vulnerable to jailbreaking attacks. We propose SEMANTICSMOOTH, a smoothing-based defense that aggregates predictions of semantically transformed copies of a given input prompt.
  arXiv  Detail & Related papers  (2024-02-25T20:36:03Z)
• Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks [41.531913152661296]
  We formulate the problem of targeted adversarial attack on Stable Diffusion and propose a framework to generate adversarial prompts. Specifically, we design a gradient-based embedding optimization method to craft reliable adversarial prompts that guide stable diffusion to generate specific images. After obtaining successful adversarial prompts, we reveal the mechanisms that cause the vulnerability of the model.
  arXiv  Detail & Related papers  (2024-01-16T12:15:39Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• Jailbroken: How Does LLM Safety Training Fail? [92.8748773632051]
  "jailbreak" attacks on early releases of ChatGPT elicit undesired behavior. We investigate why such attacks succeed and how they can be created. New attacks utilizing our failure modes succeed on every prompt in a collection of unsafe requests.
  arXiv  Detail & Related papers  (2023-07-05T17:58:10Z)
• 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.