arXiv:2608. 11815v1 Announce Type: new Abstract: Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models.
By Yaohua Liu, Yifan Guo, Jiaxin Gao
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
arXiv:2608. 10237v1 Announce Type: new Abstract: Contrastive learning and Siamese embedding models have become the foundation of modern verification systems, where decisions are governed not by discrete classification boundaries, but by relational geometry in embedding space.
By Fei Zhao, Peiyuan Zhang, Xi Li, Chengcui Zhang, Nitesh Saxena
arXiv:2605. 31219v2 Announce Type: replace-cross Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations.
By Ei Hmue Khine, Yao Li, Jiebao Sun, Shengzhu Shi, Zhichang Guo, Boying Wu
arXiv:2608.29054v1 Announce Type: new
Abstract: Graph Neural Networks (GNNs) have emerged as a cornerstone for representing complex relational dependencies in diverse multimedia tasks, particularly i...
By Shuomin Xue, Jingyuan Li, Ju Jia, Jingxuan Yu, Xiaojun Jia
The paper introduces a penalized distributionally robust optimization framework that allows an adversary to choose any distribution while incurring a Wasserstein penalty for deviating from the empirical distribution. It shows that the adversary’s problem can be reformulated as optimizing transport maps that push empirical samples to adversarial ones, proving that optimal maps are cyclically monotone. The authors argue that standard per-sample adversarial training violates this property and propose two remedies—multi-start particle ascent and input-convex neural network parameterization—to enforce cyclical monotonicity, demonstrating improved robustness and generalization in experiments on regression, image classification, and control tasks.
By Alireza Abdollahpoorrostam, Ehsan Sharifian, Buse \c{S}en, Marco Cuturi, Daniel Kuhn