Adversarial behavior plays a central role in aligning large language models with human values. However, existing alignment methods largely rely on static adversarial settings, which fundamentally limit robustness, particularly in multimodal settings with a larger attack surface. In this work, we move beyond static adversarial supervision and introduce co-evolutionary alignment with evolving attacks, instantiated by CEMMA (Co-Evolutionary Multi-Modal Alignment), an automated and adaptive framework for multimodal safety alignment. We introduce an Evolutionary Attacker that decomposes adversarial prompts into method templates and harmful intents. By employing genetic operators, including mutation, crossover, and differential evolution, it enables simple seed attacks to inherit the structural efficacy of sophisticated jailbreaks. The Adaptive Defender is iteratively updated on the synthesized hard negatives, forming a closed-loop process that adapts alignment to evolving attacks. Experiments show that the Evolutionary Attacker substantially increases red-teaming jailbreak attack success rate (ASR), while the Adaptive Defender improves robustness and generalization across benchmarks with higher data efficiency, without inducing excessive benign refusal, and remains compatible with inference-time defenses such as AdaShield.
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；Nanyang Technological University, Singapore（新加坡南洋理工大学）；University College London（伦敦大学学院）
Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games
Baidu Inc.（百度公司）；University of Chinese Academy of Sciences（中国科学院大学）；University of California, Los Angeles（加州大学洛杉矶分校）；University of Science and Technology of China（中国科学技术大学）；Zhejiang University（浙江大学）；University of Technology Sydney（悉尼科技大学）
Adversarial Prompt Distillation for Vision-Language Models
Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（上海智能信息处理实验室，计算机科学学院，复旦大学）；The Chinese University of Hong Kong, Shatin, Hong Kong（香港中文大学，沙田，香港）；The University of Hong Kong, Pokfulam, Hong Kong（香港大学，薄扶林，香港）
NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models
School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Shanghai Key Lab of Intell. Info. Processing, School of CS, Fudan University（复旦大学计算机学院智能信息处理重点实验室）；Department of Mathematics and Applications, University of Naples Federico II（那不勒斯费德里克二世大学应用数学系）；State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University（北京交通大学先进轨道交通自主运行国家重点实验室）
A Survey on Adversarial Attacks and Defenses for Diffusion Models Across Multiple Modalities
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Stanford University（斯坦福大学）；Georgia Institute of Technology（佐治亚理工学院）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；Sun Yat-sen University（中山大学）
Few-Shot Adversarial Prompt Learning on Vision-Language Models
School of Automation（自动化学院）；Beijing Institute of Technology（北京理工大学）；Sydney AI Centre（悉尼人工智能中心）；University of Sydney（悉尼大学）；Department of Computer Science（计算机科学系）；Hong Kong Baptist University（香港浸会大学）
Duke University（杜克大学）；The University of Tokyo（东京大学）；Rochester Institute of Technology（罗切斯特理工学院）；University of North Texas（北得克萨斯大学）；University of Louisville（路易斯维尔大学）
