#machine unlearning

try —

5 papers match

cs.CR2026

Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Removable Camouflage

Dongdong Zhao, Can Li, Xiang Yao +3

The paper proposes a clean‑label backdoor attack that stays dormant during training and becomes active only after specific camouflage samples are removed via machine unlearning, us…

#backdoor attacks#machine unlearning#clean-label#adversarial machine learning
cs.LG2026

Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning

Efstratios Zaradoukas, Davide Gabrielli, Bardh Prenkaj +1

The paper investigates how different reward functions affect the speed and effectiveness of reinforcement‑learning based machine unlearning for language models, proposing graded an…

#machine unlearning#reinforcement learning#reward design#language models
cs.CR2026

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

Shang Wang, Tianqing Zhu, Dayong Ye +1

The paper proposes a lightweight method to make large language models forget specific information by altering the external knowledge base of Retrieval‑Augmented Generation systems,…

#machine unlearning#retrieval-augmented generation#large language models#privacy
cs.LG2026

Inference-Time Machine Unlearning via Gated Activation Redirection

Vinícius Conte Turani, Otávio Parraga, João Vitor Boer Abitante +7

The paper proposes GUARD-IT, a gradient‑free method that modifies activations at inference time with input‑dependent rotations to erase specific data from large language models whi…

#machine unlearning#activation steering#large language models#inference-time methods
cs.LG2026

Signal-Guided Optimization for Machine Unlearning

Xujia Li, Dan Li, Jian Lou +1

The paper introduces GSUO, a guidance-signal-aware optimization framework that uses fine-grained task-specific signals to improve the effectiveness and efficiency of machine unlear…

#machine unlearning#optimization#privacy#guidance signals