paper-with-me

홈 › Papers

UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models

2024-11-03 · Sejoon Oh, Yiqiao Jin, Megha Sharma, Donghyun Kim, Eric Ma, Gaurav Verma, Srijan Kumar

Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are meticulously crafted to elicit harmful or inappropriate responses. We propose UniGuard, a novel multimodal safety guardrail that jointly considers the unimodal and cross-modal harmful signals. UniGuard trains a multimodal guardrail to minimize the likelihood of generating harmful responses in a toxic corpus. The guardrail can be seamlessly applied to any input prompt during inference with minimal computational costs. Extensive experiments demonstrate the generalizability of UniGuard across multiple modalities, attack strategies, and multiple state-of-the-art MLLMs, including LLaVA, Gemini Pro, GPT-4o, MiniGPT-4, and InstructBLIP. Notably, this robust defense mechanism maintains the models' overall vision-language understanding capabilities.

📄 PDF Abstract BibTeX arXiv:2411.01703

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
Multi-Head Attention 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

SoK: Evaluating Jailbreak Guardrails for Large Language Models

2025-06-12 · Xunguang Wang, Zhenlan Ji, Wenxuan Wang, Zongjie Li 외

Large Language Models (LLMs) have achieved remarkable progress, but their deployment has exposed critical vulnerabilities, particularly to jailbreak attacks that circumvent safety mechanisms. Guardrails--external defense…

Jailbreaking Safeguarded Text-to-Image Models via Large Language Models

2025-03-03 · Zhengyuan Jiang, Yuepeng Hu, Yuchen Yang, Yinzhi Cao 외

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the…

Language ModelingLanguage ModellingLarge Language Model

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets

2025-06-05 · Lei Hsiung, Tianyu Pang, Yung-Chen Tang, Linyue Song 외

Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies prim…

Safety Alignment

ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts

2025-08-22 · Darpan Aswal, Céline Hudelot arxiv

Large Language Models have found success in a variety of applications. However, their safety remains a concern due to the existence of various jailbreaking methods. Despite significant efforts, alignment and safety fine-…

Involuntary Jailbreak: On Self-Prompting Attacks

2025-08-18 · Yangyang Guo, Yangyan Li, Mohan Kankanhalli arxiv

In this study, we disclose a worrying new vulnerability in Large Language Models (LLMs), which we term \textbf{involuntary jailbreak}. Unlike existing jailbreak attacks, this weakness is distinct in that it does not invo…