Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

• URL: http://arxiv.org/abs/2411.11496v2
• Date: Tue, 19 Nov 2024 03:01:43 GMT
• Title: Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models
• Authors: Chenhang Cui, Gelei Deng, An Zhang, Jingnan Zheng, Yicong Li, Lianli Gao, Tianwei Zhang, Tat-Seng Chua,
• Abstract summary: Safety Snowball Agent (SSA) is a novel agent-based framework leveraging agents' autonomous and tool-using abilities to jailbreak LVLMs. Our experiments demonstrate that ours can use nearly any image to induce LVLMs to produce unsafe content, achieving high success jailbreaking rates against the latest LVLMs.
• Score: 80.77246856082742
• License:
• Abstract: Recent advances in Large Vision-Language Models (LVLMs) have showcased strong reasoning abilities across multiple modalities, achieving significant breakthroughs in various real-world applications. Despite this great success, the safety guardrail of LVLMs may not cover the unforeseen domains introduced by the visual modality. Existing studies primarily focus on eliciting LVLMs to generate harmful responses via carefully crafted image-based jailbreaks designed to bypass alignment defenses. In this study, we reveal that a safe image can be exploited to achieve the same jailbreak consequence when combined with additional safe images and prompts. This stems from two fundamental properties of LVLMs: universal reasoning capabilities and safety snowball effect. Building on these insights, we propose Safety Snowball Agent (SSA), a novel agent-based framework leveraging agents' autonomous and tool-using abilities to jailbreak LVLMs. SSA operates through two principal stages: (1) initial response generation, where tools generate or retrieve jailbreak images based on potential harmful intents, and (2) harmful snowballing, where refined subsequent prompts induce progressively harmful outputs. Our experiments demonstrate that \ours can use nearly any image to induce LVLMs to produce unsafe content, achieving high success jailbreaking rates against the latest LVLMs. Unlike prior works that exploit alignment flaws, \ours leverages the inherent properties of LVLMs, presenting a profound challenge for enforcing safety in generative multimodal systems. Our code is avaliable at \url{https://github.com/gzcch/Safety_Snowball_Agent}.

Related papers

• IDEATOR: Jailbreaking Large Vision-Language Models Using Themselves [67.30731020715496]
  We propose a novel jailbreak method named IDEATOR, which autonomously generates malicious image-text pairs for black-box jailbreak attacks. IDEATOR uses a VLM to create targeted jailbreak texts and pairs them with jailbreak images generated by a state-of-the-art diffusion model. It achieves a 94% success rate in jailbreaking MiniGPT-4 with an average of only 5.34 queries, and high success rates of 82%, 88%, and 75% when transferred to LLaVA, InstructBLIP, and Meta's Chameleon.
  arXiv  Detail & Related papers  (2024-10-29T07:15:56Z)
• Virtual Context: Enhancing Jailbreak Attacks with Special Token Injection [54.05862550647966]
  This paper introduces Virtual Context, which leverages special tokens, previously overlooked in LLM security, to improve jailbreak attacks. Comprehensive evaluations show that Virtual Context-assisted jailbreak attacks can improve the success rates of four widely used jailbreak methods by approximately 40%.
  arXiv  Detail & Related papers  (2024-06-28T11:35:54Z)
• Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt [60.54666043358946]
  This paper introduces the Bi-Modal Adversarial Prompt Attack (BAP), which executes jailbreaks by optimizing textual and visual prompts cohesively. In particular, we utilize a large language model to analyze jailbreak failures and employ chain-of-thought reasoning to refine textual prompts.
  arXiv  Detail & Related papers  (2024-06-06T13:00:42Z)
• Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing [14.094372002702476]
  Large language models (LLMs) are increasingly being adopted in a wide range of real-world applications. Recent studies have shown that LLMs are vulnerable to deliberately crafted adversarial prompts. We propose a novel defense method termed textbfLayer-specific textbfEditing (LED) to enhance the resilience of LLMs against jailbreak attacks.
  arXiv  Detail & Related papers  (2024-05-28T13:26:12Z)
• Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models [107.88745040504887]
  We study the harmlessness alignment problem of multimodal large language models (MLLMs) Inspired by this, we propose a novel jailbreak method named HADES, which hides and amplifies the harmfulness of the malicious intent within the text input. Experimental results show that HADES can effectively jailbreak existing MLLMs, which achieves an average Attack Success Rate (ASR) of 90.26% for LLaVA-1.5 and 71.60% for Gemini Pro Vision.
  arXiv  Detail & Related papers  (2024-03-14T18:24:55Z)
• Rethinking Jailbreaking through the Lens of Representation Engineering [45.70565305714579]
  The recent surge in jailbreaking methods has revealed the vulnerability of Large Language Models (LLMs) to malicious inputs. This study investigates the vulnerability of safety-aligned LLMs by uncovering specific activity patterns.
  arXiv  Detail & Related papers  (2024-01-12T00:50:04Z)
• A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily [51.63085197162279]
  Large Language Models (LLMs) are designed to provide useful and safe responses. adversarial prompts known as 'jailbreaks' can circumvent safeguards. We propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts.
  arXiv  Detail & Related papers  (2023-11-14T16:02:16Z)

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.