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:2605. 20341v2 Announce Type: replace-cross Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive.
By Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi, Omid Kashefi
arXiv:2608. 07274v1 Announce Type: cross Abstract: Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead.
By Yuhan Xie, Jingrong Huang, Chen Lyu
arXiv:2507. 01752v4 Announce Type: replace-cross Abstract: Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation.
By Ismail Labiad, Mathurin Videau, Matthieu Kowalski, Marc Schoenauer, Alessandro Leite, Julia Kempe, Olivier Teytaud
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
By Dayong Ye, Tianqing Zhu, Ruiding Huang, Xinbo Fu, Jiayang Li, Bo Liu, Huan Huo, Wanlei Zhou
arXiv:2412. 09119v3 Announce Type: replace Abstract: Machine unlearning, the process of selectively removing data from trained models, is increasingly crucial for addressing privacy concerns and knowledge gaps post-deployment.
By Youssef Allouah, Joshua Kazdan, Rachid Guerraoui, Sanmi Koyejo
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge.
The paper identifies a problem in large language model (LLM) unlearning called forget‑set misalignment, where the set of data to be forgotten does not match what the model has actually memorized. Two failure modes are described: Under Unlearning, where memorized information is omitted from the forget set, and Out‑of‑Knowledge Unlearning, where the algorithm attempts to forget knowledge the model never learned, harming performance. The authors propose CONfs, a data‑blind framework that constructs model‑aligned forget sets by eliciting the model’s memorized knowledge, and demonstrate that it achieves near‑gold standard forgetting while preserving utility better than other data‑blind methods.
By Miso Kim, Georu Lee, Seungwon Jeong, Woojin Lee
arXiv:2607. 05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challenge.
By Sahasrajit Sarmasarkar, Anastasia Koloskova, Sanmi Koyejo
arXiv:2507. 04219v5 Announce Type: replace-cross Abstract: Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.
By Yan Scholten, Sophie Xhonneux, Leo Schwinn, Stephan G\"unnemann
arXiv:2609.06346v1 Announce Type: new
Abstract: Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However,...
By Keyu Lin, Fei Ye, Qihe Liu, Shijie Zhou, Jiguo Yu
arXiv:2602. 02819v4 Announce Type: replace Abstract: Membership Inference Attacks (MIAs) aim to distinguish training points (members) from unseen data (non-members), and are widely used to quantify memorization and assess privacy risks.
By Mathieu Even, Cl\'ement Berenfeld, Linus Bleistein, Tudor Cebere, Julie Josse, Aur\'elien Bellet