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
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 UnlearningMemorizationModel State Arithmetic for Machine Unlearning
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 UnlearningmodelOn the Necessity of Output Distribution Reweighting for Effective Class Unlearning
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 UnlearningOrthogonal Soft Pruning for Efficient Class Unlearning
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 AttackVerifiable Unlearning on Edge
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 PreservingSNARKSRecalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy
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 PreservingMembership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
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 UnlearningRectifying Privacy and Efficacy Measurements in Machine Unlearning: A New Inference Attack Perspective
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 UnlearningUnlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
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 UnlearningSharpness-Aware Machine Unlearning
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 UnlearningMemorizationUCD: Unlearning in LLMs via Contrastive Decoding
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 UnlearningPrompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods
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 UnlearningTARApollo: A Posteriori Label-Only Membership Inference Attack Towards Machine Unlearning
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 AttackSoK: Machine Unlearning for Large Language Models
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 EditingCertified Unlearning for Neural Networks
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 UnlearningTowards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
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 UnlearningManagementQuantifying Cross-Modality Memorization in Vision-Language Models
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 KnowledgeRethinking Machine Unlearning in Image Generation Models
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 UnlearningSALAD: Systematic Assessment of Machine Unlearing on LLM-Aided Hardware Design
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 UnlearningTowards Machine Unlearning for Paralinguistic Speech Processing
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