paper-with-me

Papers

ToFU: Transforming How Federated Learning Systems Forget User Data

2025-09-19 · Van-Tuan Tran, Hong-Hanh Nguyen-Le, Quoc-Viet Pham arxiv

Neural networks unintentionally memorize training data, creating privacy risks in federated learning (FL) systems, such as inference and reconstruction attacks on sensitive data. To mitigate these risks and to comply with privacy regulations, Federated Unlearning (FU) has been introduced to enable participants in FL systems to remove their data's influence from the global model. However, current FU methods primarily act post-hoc, struggling to efficiently erase information deeply memorized by neural networks. We argue that effective unlearning necessitates a paradigm shift: designing FL systems inherently amenable to forgetting. To this end, we propose a learning-to-unlearn Transformation-guided Federated Unlearning (ToFU) framework that incorporates transformations during the learning process to reduce memorization of specific instances. Our theoretical analysis reveals how transformation composition provably bounds instance-specific information, directly simplifying subsequent unlearning. Crucially, ToFU can work as a plug-and-play framework that improves the performance of existing FU methods. Experiments on CIFAR-10, CIFAR-100, and the MUFAC benchmark show that ToFU outperforms existing FU baselines, enhances performance when integrated with current methods, and reduces unlearning time.

📄 PDF Abstract BibTeX arXiv:2509.15861

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data

2022-01-21 · Isha Garg, Manish Nagaraj, Kaushik Roy

Advances in Federated Learning and an abundance of user data have enabled rich collaborative learning between multiple clients, without sharing user data. This is done via a central server that aggregates learning in the…

Federated Learning

R-TOFU: Unlearning in Large Reasoning Models

2025-05-21 · Sangyeon Yoon, Wonje Jeung, Albert No

Large Reasoning Models (LRMs) embed private or copyrighted information not only in their final answers but also throughout multi-step chain-of-thought (CoT) traces, making reliable unlearning far more demanding than in s…

From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models

2026-04-15 · Wenxuan Li, Zhenfei Zhang, Mi Zhang, Geng Hong 외 arxiv

Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential remedy, prevailing paradigms rely on user-pr…

SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning

2026-08-17 · Jaewan Choi, Junyoung Yang, Sangdon Park arxiv

Machine unlearning in Large Language Models (LLMs) faces a critical trade-off between erasing target knowledge and preserving general utility. We propose SAUL (Sharpness-Aware Augmented-Lagrangian Unlearning), which form…

Hierarchical Federated Unlearning for Large Language Models

2025-10-19 · Yisheng Zhong, Zhengbang Yang, Zhuangdi Zhu arxiv

Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising …