← 研踪 PaperTrailCVF · CVPR 2026:cvf:3f5be60509ab4b410d862b345c1af4eb · 记录 #1
Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 01:57
摘要
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce models into generating harmful or undesirable content. Existing defense mechanisms often rely on external inference steps or safety alignment training, both of which are less effective and impractical when facing sophisticated adversarial perturbations in white-box scenarios. To address these challenges and bolster MLLM robustness, we introduce SAFEMLLM by adopting an adversarial training framework that alternates between an attack step for generating adversarial noise and a model updating step. At the attack step, SAFEMLLM generates adversarial perturbations through a newly proposed contrastive embedding attack (CoE-Attack), which optimizes token embeddings under a contrastive objective. SAFEMLLM then updates model parameters to neutralize the perturbation effects while preserving model utility on benign inputs. We evaluate SAFEMLLM across multiple MLLMs and six jailbreak methods spanning multiple modalities. Experimental results show that SAFEMLLM effectively defends against diverse attacks, maintaining robust performance and utilities.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Towards Robust Multimodal Large Language Models Against Jailbreak Attacks
While multimodal large language models (MLLMs) have achieved remarkable success in recent advancements, their susceptibility to jailbreak attacks has come to light. In such attacks, adversaries exploit carefully crafted prompts to coerce models into generating harmful or undesirable content. Existing defense mechanisms often rely on external inference steps or safety alignment training, both of which are less effective and impractical when facing sophisticated adversarial perturbations in white-box scenarios. To address these challenges and bolster MLLM robustness, we introduce SAFEMLLM by adopting an adversarial training framework that alternates between an attack step for generating adversarial noise and a model updating step. At the attack step, SAFEMLLM generates adversarial perturbations through a newly proposed contrastive embedding attack (CoE-Attack), which optimizes token embeddings under a contrastive objective. SAFEMLLM then updates model parameters to neutralize the perturbation effects while preserving model utility on benign inputs. We evaluate SAFEMLLM across multiple MLLMs and six jailbreak methods spanning multiple modalities. Experimental results show that SAFEMLLM effectively defends against diverse attacks, maintaining robust performance and utilities.
查看此版本解读 →查看此版本原文 ↗