arXiv:2610.06977v1 Announce Type: cross
Abstract: Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples, especially in black-box settings where only open-sou...
By Xiaojun Jia, Simeng Qin, Yiming Li, Jie Liao, Sensen Gao, Ke Ma, Yang Liu, Xiaochun Cao
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
By Lijia Yu, Jiuxin Cao, Yuchen Qiang, Changhao Chen, Yifei Huang, Bo Liu
arXiv:2511. 17688v2 Announce Type: replace-cross Abstract: Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs.
By Quan Liu, Feng Ye, Chenhao Lu, Shuming Zhen, Guanliang Huang, Lunzhe Chen, Xudong Ke
arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.
By Dongpeng Zhang, Ke Ma, Yangbangyan Jiang, Gaozheng Pei, Longtao Huang, Qianqian Xu, Qingming Huang
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
The paper introduces Inverse Knowledge Distillation (IKD), an attack‑agnostic technique that enhances adversarial transferability by maximizing the discrepancy between benign and adversarial prediction distributions on a surrogate model. IKD employs a CE/KL‑equivalent soft‑label objective to push adversarial predictions away from a fixed benign anchor, leveraging Fisher‑sensitive surrogate directions. The authors provide theoretical analysis showing CE and KL induce identical gradients, derive a lower bound on Fisher‑subspace overlap, and demonstrate through extensive ImageNet experiments that IKD consistently improves black‑box attack performance across CNN, ViT, and defended models.
By Wenyuan Wu, Yuan Sun, Yingke Chen, Chao Su, Xi Peng, Dezhong Peng, Xu Wang