paper-with-me

Papers

ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer

2023-01-01 · CVPR 2023 1 · Shen Lin, XiaoYu Zhang, Chenyang Chen, Xiaofeng Chen, Willy Susilo

Machine unlearning can fortify the privacy and security of machine learning applications. Unfortunately, the exact unlearning approaches are inefficient, and the approximate unlearning approaches are unsuitable for complicated CNNs. Moreover, the approximate approaches have serious security flaws because even unlearning completely different data points can produce the same contribution estimation as unlearning the target data points. To address the above problems, we try to define machine unlearning from the knowledge perspective, and we propose a knowledge-level machine unlearning method, namely ERM-KTP. Specifically, we propose an entanglement-reduced mask (ERM) structure to reduce the knowledge entanglement among classes during the training phase. When receiving the unlearning requests, we transfer the knowledge of the non-target data points from the original model to the unlearned model and meanwhile prohibit the knowledge of the target data points via our proposed knowledge transfer and prohibition (KTP) method. Finally, we will get the unlearned model as the result and delete the original model to accomplish the unlearning process. Especially, our proposed ERM-KTP is an interpretable unlearning method because the ERM structure and the crafted masks in KTP can explicitly explain the operation and the effect of unlearning data points. Extensive experiments demonstrate the effectiveness, efficiency, high fidelity, and scalability of the ERM-KTP unlearning method.

📄 PDF Abstract BibTeX

Code (1)

ruiyun-ml/erm-ktp 공식 구현 pytorch

Tasks

Machine UnlearningTransfer Learning

Similar Papers 제목 키워드 기반

Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs

2026-01-09 · Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard, Zhuan Shi 외 arxiv

As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing research on machine unlearning has primarily…

Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation

2023-12-28 · Hyunjune Kim, Sangyong Lee, Simon S. Woo

Recently, serious concerns have been raised about the privacy issues related to training datasets in machine learning algorithms when including personal data. Various regulations in different countries, including the GDP…

Knowledge DistillationMachine Unlearning

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition

2026-05-14 · Shen Lin, Jing Lin, Junhao Dong, Piotr Koniusz 외 arxiv

Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affecting unrelated semantics. This issue is esp…

Concept Unlearning in Large Language Models via Self-Constructed Knowledge Triplets

2025-09-19 · Tomoya Yamashita, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura 외 arxiv

Machine Unlearning (MU) has recently attracted considerable attention as a solution to privacy and copyright issues in large language models (LLMs). Existing MU methods aim to remove specific target sentences from an LLM…

Knowledge Graphs

Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility

2026-06-02 · Chaoyi Xiang, Olga Ohrimenko, Benjamin I. P. Rubinstein, Lea Frermann arxiv

Large language models (LLMs) can memorize sensitive facts, motivating unlearning methods that remove targeted knowledge without costly retraining. However, unlearning research remains heavily English-centric. We study mu…