arXiv:2511. 13749v2 Announce Type: replace Abstract: Deep neural networks are known to be vulnerable to adversarial perturbations, which are small, carefully crafted inputs that lead to incorrect predictions.
By Ci Lin, Tet Yeap, Iluju Kiringa
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
arXiv:2606. 14078v1 Announce Type: cross Abstract: Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks.
By Zhenqian Zhu, Yamin Hu, Yujiang Liu, Luping Wei, Wenbo Hou, Bin Li, Haodong Li, Wenjian Luo
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
arXiv:2606. 11123v1 Announce Type: new Abstract: Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation.
By Gauthier Boeshertz, Razvan Pascanu, Claudia Clopath
arXiv:2606. 00738v1 Announce Type: cross Abstract: Adversarial Training (AT) is a leading defense against adversarial examples but often suffers from Catastrophic Overfitting (CO) in efficient single-step variants, where robustness to multi-step attacks collapses despite high single-step performance.
By Mazdak Teymourian, Ramtin Moslemi, Farzan Rahmani, Mohammad Hossein Rohban