| Challenge: | Existing studies on the safety of large language models (LLMs) with human values have focused on the integration of multi-modal user input into these models. |
| Approach: | They propose a method to bypass safety constraints of large language models by using poisoned images instead of original textual captions. |
| Outcome: | The proposed attack bypasses safety constraints of large language models (VLMs) by replacing the original textual captions with malicious jailbreak prompts. |
Similar Papers
Jailbreak Large Vision-Language Models Through Multi-Modal Linkage (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods to jailbreak large vision-language models fail against cutting-edge models such as GPT-4o, despite having undergone safety alignment training. |
| Approach: | They propose a new framework for jailbreaking large vision-language models that uses an encryption-decryption process to mitigate the over-exposure of harmful information. |
| Outcome: | The proposed framework jailbreaks GPT-4o with 99.40% success rates on SafeBench, 98.81% on MM-SafeBench and 99.07% on HADES-Dataset. |
A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated capabilities for generating content that could be deemed harmful. |
| Approach: | They conduct a comprehensive analysis of existing studies on jailbreaking LLMs and their defense techniques. |
| Outcome: | The proposed techniques underperform existing white-box attacks and include special tokens significantly affects the likelihood of successful attacks. |
Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking (2026.acl-long)
Copied to clipboard
| Challenge: | Existing attacks optimize image perturbations to maximize harmful output likelihood, but suffer from slow convergence due to gradient conflict between adversarial objectives and the model’s safety-retrieval mechanism. |
| Approach: | They propose a push-pull approach which suppresses attention to system-prompt tokens and anchors generation on adversarial image features to avoid collisions. |
| Outcome: | The proposed approach reduces gradient conflict by 45% and achieves 94.4% attack success rate on Qwen-VL (vs. 68.8% baseline) with 40% fewer iterations. |
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Understanding how jailbreaking works remains limited, hindering the development of effective defense strategies. |
| Approach: | They propose a new mechanism that adaptively constrains activations within the safety boundary and propose 'Activation Boundary Defense' to enhance its effectiveness. |
| Outcome: | The proposed defense achieves an average Defense Success Rate (DSR) of over 98% against various jailbreak attacks, with less than 2% impact on the model’s general capabilities. |
Safety Guardrails of Large Language Models Are Vulnerable to Value-Driven Adversarial Prompting (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak attacks against large language models (LLMs) can be divided into white-box attacks and black-box attack. |
| Approach: | They propose a value-driven jailbreak attack that exploits the phenomenon that large language models agree with humans to induce LLMs to affirm the moral value of harmful tasks. |
| Outcome: | Extensive experiments on five state-of-the-art (SOTA) LLMs show the value-driven jailbreak attack achieves an average attack success rate (ASR) of 91.8% on JailbreakBench and 95.2% on the AdvBench subset. |
Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective (2025.coling-main)
Copied to clipboard
Tianlong Li, Zhenghua Wang, Wenhao Liu, Muling Wu, Shihan Dou, Changze Lv, Xiaohua Wang, Xiaoqing Zheng, Xuanjing Huang
| Challenge: | Recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) however, limited research into the underlying mechanisms that make LLMs vulnerable to such attacks has been conducted. |
| Approach: | They propose that LLMs' self-safeguarding capability is linked to specific activity patterns within their representation space. |
| Outcome: | The proposed models can be detected with a few pairs of contrastive queries, and the robustness can be manipulated by weakening or strengthening these patterns. |
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. |
| Approach: | They propose to leverage hidden representations into existing jailbreak targets to move the attacks along the acceptance direction. |
| Outcome: | The proposed methods are validated using the objective of existing jailbreak attacks. |
\mathsf{Con Instruction}: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities (2025.acl-long)
Copied to clipboard
| Challenge: | Existing attacks communicate instruction through text, accompanied by a toxic image or audio . a novel gray-box attack method generates adversarial images or audio to convey harmful instructions to MLLMs . |
| Approach: | They propose a gray-box attack method that generates adversarial images or audio to convey specific harmful instructions to MLLMs by following non-textual instruction. |
| Outcome: | The proposed method achieves highest success rates on visual and audio-language models . larger models are more susceptible toCon Instruction, compared to their underlying models - the results will be released . |
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race? (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have focused on the models, neglecting the full deployment pipeline . previous studies have underestimated the practical success of these attacks . |
| Approach: | They evaluate the effectiveness of jailbreak attacks targeting LLM safety alignment . they highlight critical gaps and call for further refinement of detection accuracy and usability . |
| Outcome: | The proposed attacks can detect at least one safety filter across the entire deployment pipeline. |
Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring (2026.acl-long)
Copied to clipboard
| Challenge: | Large Vision-Language Models (LVLMs) are vulnerable to a growing array of multimodal jailbreak attacks, necessitating a generalizable defense that is efficient for practical deployment. |
| Approach: | They propose a framework that uses a lightweight projection to separate benign and malicious inputs in safety-critical layers. |
| Outcome: | The proposed framework enables a simple yet powerful contrastive score that differentiates true malicious intent from mere distribution shift. |