paper-with-me

Papers Machine Unlearning

“Machine Unlearning” 태그가 달린 논문 438편 · 필터 해제

What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests

2025-07-15 · Dimitri Staufer

Large Language Models (LLMs) can memorize and reveal personal information, raising concerns regarding compliance with the EU's GDPR, particularly the Right to Be Forgotten (RTBF). Existing machine unlearning methods assu…

Machine UnlearningMemorization

Model State Arithmetic for Machine Unlearning

2025-06-26 · Keivan Rezaei, Mehrdad Saberi, Abhilasha Ravichander, Soheil Feizi

Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance. Eliminating the influence of suc…

Machine Unlearningmodel

On the Necessity of Output Distribution Reweighting for Effective Class Unlearning

2025-06-25 · Yian Wang, Ali Ebrahimpour-Boroojeny, Hari Sundaram

In this work, we introduce an output-reweighting unlearning method, RWFT, a lightweight technique that erases an entire class from a trained classifier without full retraining. Forgetting specific classes from trained mo…

Machine Unlearning

Orthogonal Soft Pruning for Efficient Class Unlearning

2025-06-24 · Qinghui Gong, Xue Yang, Xiaohu Tang

Machine unlearning aims to selectively remove class-specific knowledge from pretrained neural networks to satisfy privacy regulations such as the GDPR. Existing methods typically face a trade-off between unlearning speed…

Inference AttackMachine UnlearningMembership Inference Attack

Verifiable Unlearning on Edge

2025-06-24 · Mohammad M Maheri, Alex Davidson, Hamed Haddadi

Machine learning providers commonly distribute global models to edge devices, which subsequently personalize these models using local data. However, issues such as copyright infringements, biases, or regulatory requireme…

Machine UnlearningPrivacy PreservingSNARKS

Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy

2025-06-24 · Zhihao Sui, Liang Hu, Jian Cao, Dora D. Liu 외

Machine Unlearning (MU) technology facilitates the removal of the influence of specific data instances from trained models on request. Despite rapid advancements in MU technology, its vulnerabilities are still underexplo…

Knowledge DistillationLearning with noisy labelsMachine UnlearningPrivacy Preserving

Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble

2025-06-16 · Zhiqi Wang, Chengyu Zhang, Yuetian Chen, Nathalie Baracaldo 외

Membership inference attacks (MIAs) pose a significant threat to the privacy of machine learning models and are widely used as tools for privacy assessment, auditing, and machine unlearning. While prior MIA research has …

Machine Unlearning

Rectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective

2025-06-16 · Nima Naderloui, Shenao Yan, Binghui Wang, Jie Fu 외

Machine unlearning focuses on efficiently removing specific data from trained models, addressing privacy and compliance concerns with reasonable costs. Although exact unlearning ensures complete data removal equivalent t…

Inference AttackMachine Unlearning

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs

2025-06-16 · YiWei Chen, Soumyadeep Pal, Yimeng Zhang, Qing Qu 외

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard…

Machine Unlearning

Sharpness-Aware Machine Unlearning

2025-06-16 · Haoran Tang, Rajiv Khanna

We characterize the effectiveness of Sharpness-aware minimization (SAM) under machine unlearning scheme, where unlearning forget signals interferes with learning retain signals. While previous work prove that SAM improve…

DenoisingMachine UnlearningMemorization

UCD: Unlearning in LLMs via Contrastive Decoding

2025-06-12 · Vinith M. Suriyakumar, Ayush Sekhari, Ashia Wilson

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm tha…

Machine Unlearning

Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods

2025-06-11 · Yeonwoo Jang, Shariqah Hossain, Ashwin Sreevatsa, Diogo Cruz

In this work, we show that some machine unlearning methods may fail when subjected to straightforward prompt attacks. We systematically evaluate eight unlearning techniques across three model families, and employ output-…

Machine UnlearningTAR

Apollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning

2025-06-11 · Liou Tang, James Joshi, Ashish Kundu

Machine Unlearning (MU) aims to update Machine Learning (ML) models following requests to remove training samples and their influences on a trained model efficiently without retraining the original ML model from scratch.…

Inference AttackMachine UnlearningMembership Inference Attack

SoK: Machine Unlearning for Large Language Models

2025-06-10 · Jie Ren, Yue Xing, Yingqian Cui, Charu C. Aggarwal 외

Large language model (LLM) unlearning has become a critical topic in machine learning, aiming to eliminate the influence of specific training data or knowledge without retraining the model from scratch. A variety of tech…

Large Language ModelMachine UnlearningModel Editing

Certified Unlearning for Neural Networks

2025-06-08 · Anastasia Koloskova, Youssef Allouah, Animesh Jha, Rachid Guerraoui 외

We address the problem of machine unlearning, where the goal is to remove the influence of specific training data from a model upon request, motivated by privacy concerns and regulatory requirements such as the "right to…

Machine Unlearning

Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness

2025-06-06 · Cheng-Long Wang, Qi Li, Zihang Xiang, Yinzhi Cao 외

Growing concerns over data privacy and security highlight the importance of machine unlearning--removing specific data influences from trained models without full retraining. Techniques like Membership Inference Attacks …

Machine UnlearningManagement

Quantifying Cross-Modality Memorization in Vision-Language Models

2025-06-05 · Yuxin Wen, Yangsibo Huang, Tom Goldstein, Ravi Kumar 외

Understanding what and how neural networks memorize during training is crucial, both from the perspective of unintentional memorization of potentially sensitive information and from the standpoint of effective knowledge …

Machine UnlearningMemorizationWorld Knowledge

Rethinking Machine Unlearning in Image Generation Models

2025-06-03 · Renyang Liu, Wenjie Feng, Tianwei Zhang, Wei Zhou 외

With the surge and widespread application of image generation models, data privacy and content safety have become major concerns and attracted great attention from users, service providers, and policymakers. Machine unle…

BenchmarkingImage GenerationMachine Unlearning

SALAD: Systematic Assessment of Machine Unlearing on LLM-Aided Hardware Design

2025-06-02 · Zeng Wang, Minghao Shao, Rupesh Karn, Likhitha Mankali 외

Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog eval…

Code GenerationMachine Unlearning

Towards Machine Unlearning for Paralinguistic Speech Processing

2025-06-02 · Orchid Chetia Phukan, Girish, Mohd Mujtaba Akhtar, Shubham Singh 외

In this work, we pioneer the study of Machine Unlearning (MU) for Paralinguistic Speech Processing (PSP). We focus on two key PSP tasks: Speech Emotion Recognition (SER) and Depression Detection (DD). To this end, we pro…

Depression DetectionEmotion RecognitionMachine UnlearningSpeech Emotion Recognition
1–20 / 438 다음 →