arXiv:2607. 05908v1 Announce Type: new Abstract: Real-world data distributions evolve over time, inducing temporal distribution shift that can substantially degrade the reliability of deployed machine learning systems.
By Robin Holzinger (Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA), Riccardo Colletti (Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA)
FSPGD introduces a feature-space black-box attack for semantic segmentation that targets intermediate representations rather than just output logits. The method uses a dual loss: an external loss to disrupt cross-model feature alignment and an internal loss to reduce consistency among same-class instances. Experiments on Pascal VOC 2012 and Cityscapes show that FSPGD outperforms existing logit-level and segmentation-specific attacks across CNN and Transformer backbones, and its adversarial examples improve robustness when used for training.
By Eun-Sol Park, MiSo Park, Yong-Goo Shin
arXiv:2607. 11228v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs) demonstrate remarkable capabilities, they remain highly susceptible to embedded social biases.
By Anqi Li, Jie Zhang, Zhongqi Wang, Songkai Xue, Jiahao Wang, Shiguang Shan, Xilin Chen
The paper introduces MOSAIC, a large adversarial benchmark for detecting AI-generated text, and presents NeuroStat, a new framework that combines token‑level probabilistic logits with deep semantic hidden states from a single language model. NeuroStat fuses these signals via Macro‑State Residual Modulation and uses orthogonal and contrastive losses to learn complementary representations. Experiments show that NeuroStat outperforms existing methods on MOSAIC, achieving superior robustness against adversarial attacks.
By Peiming Li, Yifan Wang, Zhiyuan Hu, Shiyu Li, Zheng Wei, Yang Tang
arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.
By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang
The paper introduces Dynamic DAE Guardrails (DSG), a method that uses Dynamic Sparse Autoencoders to perform precision unlearning in large language models. DSG leverages principled feature selection and a dynamic classifier to target activation-based unlearning, outperforming existing gradient‑based methods in terms of computational efficiency, stability, sequential unlearning, resistance to relearning attacks, data efficiency, and interpretability.
By Aashiq Muhamed, Jacopo Bonato, Mona Diab, Virginia Smith