Papers Machine Unlearning
“Machine Unlearning” 태그가 달린 논문 438편 · 필터 해제
A Survey on Unlearnable Data
Unlearnable data (ULD) has emerged as an innovative defense technique to prevent machine learning models from learning meaningful patterns from specific data, thus protecting data privacy and security. By introducing per…
Machine UnlearningSurveyBuyer-Initiated Auction Mechanism for Data Redemption in Machine Unlearning
The rapid growth of artificial intelligence (AI) has raised privacy concerns over user data, leading to regulations like the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA). With …
Machine UnlearningEfficient Verified Machine Unlearning For Distillation
Growing data privacy demands, driven by regulations like GDPR and CCPA, require machine unlearning methods capable of swiftly removing the influence of specific training points. Although verified approaches like SISA, us…
Knowledge DistillationMachine UnlearningLoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty
We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths the prediction probabilities of the mode…
Machine UnlearningMemorizationFROG: Fair Removal on Graphs
As compliance with privacy regulations becomes increasingly critical, the growing demand for data privacy has highlighted the significance of machine unlearning in many real world applications, such as social network and…
FairnessMachine UnlearningRecommendation SystemsMachine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Machine unlearning methods have become increasingly important for selective concept removal in large pre-trained models. While recent work has explored unlearning in Euclidean contrastive vision-language models, the effe…
Contrastive LearningMachine UnlearningDeep Contrastive Unlearning for Language Models
The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success…
Machine UnlearningRobust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
Model quantization enables efficient deployment of deep neural networks on edge devices through low-bit parameter representation, yet raises critical challenges for implementing machine unlearning (MU) under data privacy…
Machine UnlearningQuantizationPEBench: A Fictitious Dataset to Benchmark Machine Unlearning for Multimodal Large Language Models
In recent years, Multimodal Large Language Models (MLLMs) have demonstrated remarkable advancements in tasks such as visual question answering, visual understanding, and reasoning. However, this impressive progress relie…
Machine UnlearningPrivacy PreservingQuestion AnsweringVisual Question AnsweringSafety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning
Recent vision-language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. However, their susceptibility to generating harmful content when exposed to u…
Machine UnlearningGroup-robust Machine Unlearning
Machine unlearning is an emerging paradigm to remove the influence of specific training data (i.e., the forget set) from a model while preserving its knowledge of the rest of the data (i.e., the retain set). Previous app…
FairnessMachine UnlearningAre We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
Machine unlearning is a process to remove specific data points from a trained model while maintaining the performance on retain data, addressing privacy or legal requirements. Despite its importance, existing unlearning …
Machine UnlearningSemantic SimilaritySemantic Textual SimilarityTransfer LearningLearning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
Machine Unlearning has recently garnered significant attention, aiming to selectively remove knowledge associated with specific data while preserving the model's performance on the remaining data. A fundamental challenge…
Machine UnlearningNode-level Contrastive Unlearning on Graph Neural Networks
Graph unlearning aims to remove a subset of graph entities (i.e. nodes and edges) from a graph neural network (GNN) trained on the graph. Unlike machine unlearning for models trained on Euclidean-structured data, effecti…
Graph Neural Networkgraph partitioningMachine UnlearningData Unlearning in Diffusion Models
Recent work has shown that diffusion models memorize and reproduce training data examples. At the same time, large copyright lawsuits and legislation such as GDPR have highlighted the need for erasing datapoints from dif…
Machine UnlearningMemorizationAMUN: Adversarial Machine UNlearning
Machine unlearning, where users can request the deletion of a forget dataset, is becoming increasingly important because of numerous privacy regulations. Initial works on ``exact'' unlearning (e.g., retraining) incur lar…
image-classificationImage ClassificationMachine UnlearningSCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications
Deep learning (DL) enabled semantic communications leverage DL to train encoders and decoders (codecs) to extract and recover semantic information. However, most semantic training datasets contain personal private inform…
Machine UnlearningSemantic CommunicationTAPE: Tailored Posterior Difference for Auditing of Machine Unlearning
With the increasing prevalence of Web-based platforms handling vast amounts of user data, machine unlearning has emerged as a crucial mechanism to uphold users' right to be forgotten, enabling individuals to request the …
Machine UnlearningErasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation--ensuring that models forget not only specific training samples but also related implicit knowledge. To this …
Machine UnlearningHolistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal
In recent years, Large Language Models (LLMs) have faced increasing demands to selectively remove sensitive information, protect privacy, and comply with copyright regulations through unlearning, by Machine Unlearning. W…
Dataset GenerationKnowledge GraphsMachine UnlearningMemorization