1
A survey of security and privacy issues of machine unlearning
2
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
3
MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
4
Towards Efficient Target-Level Machine Unlearning Based on Essential Graph
5
Decoupling the Class Label and the Target Concept in Machine Unlearning
6
A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks
7
Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
8
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
9
Federated unlearning for medical image analysis
10
Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images
11
Digital forgetting in large language models: a survey of unlearning methods
12
Towards efficient and effective unlearning of large language models for recommendation
13
Dissecting Language Models: Machine Unlearning via Selective Pruning
14
FAST: Adopting Federated Unlearning to Eliminating Malicious Terminals at Server Side
15
Learn to Unlearn: Insights Into Machine Unlearning
16
Federated Unlearning: a Perspective of Stability and Fairness
17
Machine Unlearning for Image-to-Image Generative Models
18
Towards Effective and General Graph Unlearning via Mutual Evolution
19
Machine Unlearning: An Overview of the Paradigm Shift in the Evolution of AI
20
Machine Unlearning Through Fine-Grained Model Parameters Perturbation
21
Communication Efficient and Provable Federated Unlearning
22
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation
23
FedCIO: Efficient Exact Federated Unlearning with Clustering, Isolation, and One-shot Aggregation
24
FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs
25
Exact-Fun: An Exact and Efficient Federated Unlearning Approach
26
A Survey on Federated Unlearning: Challenges, Methods, and Future Directions
27
Unlearn What You Want to Forget: Efficient Unlearning for LLMs
28
Fast Model Debias with Machine Unlearning
29
In-Context Unlearning: Language Models as Few Shot Unlearners
30
Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems
31
Who's Harry Potter? Approximate Unlearning in LLMs
32
Adapt then Unlearn: Exploiting Parameter Space Semantics for Unlearning in Generative Adversarial Networks
33
FRAMU: Attention-Based Machine Unlearning Using Federated Reinforcement Learning
34
Explainability for Large Language Models: A Survey
35
Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation
36
Towards Understanding and Enhancing Robustness of Deep Learning Models against Malicious Unlearning Attacks
37
Fair Machine Unlearning: Data Removal while Mitigating Disparities
38
A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
39
BFU: Bayesian Federated Unlearning with Parameter Self-Sharing
40
A Survey on Evaluation of Large Language Models
41
DeltaBoost: Gradient Boosting Decision Trees with Efficient Machine Unlearning
42
One-Shot Machine Unlearning with Mnemonic Code
43
ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer
44
Machine Unlearning: Its Nature, Scope, and Importance for a “Delete Culture”
45
KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment
46
SAFE: Machine Unlearning With Shard Graphs
47
Get Rid of Your Trail: Remotely Erasing Backdoors in Federated Learning
48
Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection
49
To be forgotten or to be fair: unveiling fairness implications of machine unlearning methods
50
Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning
51
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
52
Unlearning Graph Classifiers with Limited Data Resources
53
Proof of Unlearning: Definitions and Instantiation
54
Federated Unlearning for On-Device Recommendation
55
Verifiable and Provably Secure Machine Unlearning
56
Machine Unlearning for Image Retrieval: A Generative Scrubbing Approach
57
Knowledge Unlearning for Mitigating Privacy Risks in Language Models
58
Machine Unlearning Method Based On Projection Residual
59
An Introduction to Machine Unlearning
60
Federated Unlearning: Guarantee the Right of Clients to Forget
61
Evaluating Machine Unlearning via Epistemic Uncertainty
62
Federated Unlearning: How to Efficiently Erase a Client in FL?
63
Athena: Probabilistic Verification of Machine Unlearning
64
Measuring Forgetting of Memorized Training Examples
65
Certifiable Unlearning Pipelines for Logistic Regression: An Experimental Study
66
Certified Graph Unlearning
67
Unlearning Protected User Attributes in Recommendations with Adversarial Training
68
Few-Shot Unlearning by Model Inversion
69
Quark: Controllable Text Generation with Reinforced Unlearning
70
VeriFi: Towards Verifiable Federated Unlearning
71
Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
72
Deep Unlearning via Randomized Conditionally Independent Hessians
73
A Survey on Graph Representation Learning Methods
74
Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis
75
Knowledge Removal in Sampling-based Bayesian Inference
76
Continual Learning and Private Unlearning
77
The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
78
PUMA: Performance Unchanged Model Augmentation for Training Data Removal
79
Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten
80
Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations
81
Bounding Membership Inference
82
Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning
83
Efficiently Maintaining Next Basket Recommendations under Additions and Deletions of Baskets and Items
84
Federated Unlearning with Knowledge Distillation
85
Backdoor Defense with Machine Unlearning
86
Recommendation Unlearning
87
Zero-Shot Machine Unlearning
88
Anatomizing Bias in Facial Analysis
89
An Investigation on Learning, Polluting, and Unlearning the Spam Emails for Lifelong Learning
90
Forget-SVGD: Particle-Based Bayesian Federated Unlearning
91
Machine unlearning via GAN
92
Fast Yet Effective Machine Unlearning
93
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
94
Federated Unlearning via Class-Discriminative Pruning
95
Prototype Learning for Interpretable Respiratory Sound Analysis
96
Unrolling SGD: Understanding Factors Influencing Machine Unlearning
97
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
98
EMA: Auditing Data Removal from Trained Models
99
Machine Unlearning of Features and Labels
100
Machine Unlearning: Its Need and Implementation Strategies
101
Revisiting Machine Learning Training Process for Enhanced Data Privacy
102
RevFRF: Enabling Cross-Domain Random Forest Training With Revocable Federated Learning
103
Learning with Selective Forgetting
104
SSSE: Efficiently Erasing Samples from Trained Machine Learning Models
105
Certifiable Machine Unlearning for Linear Models
106
FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models
107
Knowledge-Adaptation Priors
108
HedgeCut: Maintaining Randomised Trees for Low-Latency Machine Unlearning
109
Adaptive Machine Unlearning
110
A Unified PAC-Bayesian Framework for Machine Unlearning via Information Risk Minimization
111
DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
112
Knowledge Neurons in Pretrained Transformers
113
JUDO: Just-in-time rumour detection in streaming social platforms
115
Proof-of-Learning: Definitions and Practice
116
Remember What You Want to Forget: Algorithms for Machine Unlearning
117
Distilling Causal Effect of Data in Class-Incremental Learning
118
Machine Unlearning via Algorithmic Stability
119
FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning
120
Bayesian Inference Forgetting
121
Unlearnable Examples: Making Personal Data Unexploitable
122
Detection of rumor conversations in Twitter using graph convolutional networks
123
Coded Machine Unlearning
125
Mixed-Privacy Forgetting in Deep Networks
126
Class Clown: Data Redaction in Machine Unlearning at Enterprise Scale
127
Online Forgetting Process for Linear Regression Models
128
Fair Attribute Classification through Latent Space De-biasing
129
Enhancing Transferability of Black-Box Adversarial Attacks via Lifelong Learning for Speech Emotion Recognition Models
130
Variational Bayesian Unlearning
131
Amnesiac Machine Learning
132
Learning Parameter Distributions to Detect Concept Drift in Data Streams
133
Deep learning-based unlearning of dataset bias for MRI harmonisation and confound removal
134
Unlearning Scanner Bias for MRI Harmonisation in Medical Image Segmentation
135
Graph Representation Learning
136
Machine Unlearning for Random Forests
137
Boosting methods for multi-class imbalanced data classification: an experimental review
138
How Does Data Augmentation Affect Privacy in Machine Learning?
139
Descent-to-Delete: Gradient-Based Methods for Machine Unlearning
140
DeltaGrad: Rapid retraining of machine learning models
141
Influence Functions in Deep Learning Are Fragile
142
Deep Autoencoding Topic Model With Scalable Hybrid Bayesian Inference
144
When Machine Unlearning Jeopardizes Privacy
145
Open Graph Benchmark: Datasets for Machine Learning on Graphs
146
Generating and Protecting Against Adversarial Attacks for Deep Speech-Based Emotion Recognition Models
147
Have you forgotten? A method to assess if machine learning models have forgotten data
148
Learn to Forget: Machine Unlearning via Neuron Masking
149
Automating Botnet Detection with Graph Neural Networks
150
Towards Probabilistic Verification of Machine Unlearning
151
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations
152
Adversarial Attacks and Defenses in Deep Learning
153
Learning Mathematics “Asyik” with Youtube Educative Media
154
PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models
155
Formalizing Data Deletion in the Context of the Right to Be Forgotten
156
Approximate Data Deletion from Machine Learning Models: Algorithms and Evaluations
157
The EU General Data Protection Regulation (GDPR)
158
Machine unlearning: linear filtration for logit-based classifiers
159
Bayesian Neural Networks with Weight Sharing Using Dirichlet Processes
160
Analyzing Information Leakage of Updates to Natural Language Models
161
On Training Deep Neural Networks Using a Streaming Approach
163
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
164
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
165
Certified Data Removal from Machine Learning Models
166
Lifelong Anomaly Detection Through Unlearning
167
Aleatoric and epistemic uncertainty in machine learning: an introduction to concepts and methods
168
Graph representation learning: a survey
169
A Survey on Bias and Fairness in Machine Learning
170
Making AI Forget You: Data Deletion in Machine Learning
171
Making Machine Learning Forget
172
Zero-shot Knowledge Transfer via Adversarial Belief Matching
173
A novel online incremental and decremental learning algorithm based on variable support vector machine
174
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
175
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
176
Simplifying Graph Convolutional Networks
177
Uncertainty in Neural Networks: Approximately Bayesian Ensembling
178
Algorithms that remember: model inversion attacks and data protection law
179
AI can be sexist and racist — it’s time to make it fair
180
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
181
Efficient Repair of Polluted Machine Learning Systems via Causal Unlearning
182
Deep Face Recognition: A Survey
183
Continual Lifelong Learning with Neural Networks: A Review
184
A Progressive Batching L-BFGS Method for Machine Learning
185
A Geometric View of Optimal Transportation and Generative Model
186
Humans forget, machines remember: Artificial intelligence and the Right to Be Forgotten
187
The EU General Data Protection Regulation (GDPR)
188
Retaining Data from Streams of Social Platforms with Minimal Regret
189
Understanding Black-box Predictions via Influence Functions
190
Opening the Black Box of Deep Neural Networks via Information
191
Overcoming catastrophic forgetting in neural networks
192
Membership Inference Attacks Against Machine Learning Models
193
Deep Learning with Differential Privacy
194
A Multi-Batch L-BFGS Method for Machine Learning
195
Communication-Efficient Learning of Deep Networks from Decentralized Data
196
The MovieLens Datasets: History and Context
197
LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
198
Towards Making Systems Forget with Machine Unlearning
199
Deep learning and the information bottleneck principle
200
New Insights and Perspectives on the Natural Gradient Method
201
Incremental and decremental training for linear classification
202
Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing
203
The Algorithmic Foundations of Differential Privacy
204
Total variation distance and the distribution of relative information
205
The EU Proposal for a General Data Protection Regulation and the roots of the 'right to be forgotten'
206
From extractable collision resistance to succinct non-interactive arguments of knowledge, and back again
207
Learning Word Vectors for Sentiment Analysis
208
Multiple Incremental Decremental Learning of Support Vector Machines
209
Differentially Private Empirical Risk Minimization
210
Learning your identity and disease from research papers: information leaks in genome wide association study
211
ImageNet: A large-scale hierarchical image database
212
Collective Classification in Network Data
213
Differential Privacy: A Survey of Results
214
Incremental and Decremental Learning for Linear Support Vector Machines
215
Extremely randomized trees
216
Incremental and Decremental Proximal Support Vector Classification using Decay Coefficients
217
Multicategory Incremental Proximal Support Vector Classifiers
218
Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state.
219
The information bottleneck method
220
Efficient noise-tolerant learning from statistical queries
221
On Information and Sufficiency
222
the ML model due to the stochastic nature of the training procedure [12]
223
UnlearnCanvas: A Stylized Image Dataset to Benchmark Machine Unlearning for Diffusion Models
224
Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers
225
Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models
226
A Decision-Making Process to Implement the 'Right to Be Forgotten' in Machine Learning
227
Machine Unlearning Methodology Based on Stochastic Teacher Network
228
Unlearning Bias in Language Models by Partitioning Gradients
229
Fast Federated Machine Unlearning with Nonlinear Functional Theory
230
FedRecovery: Differentially Private Machine Unlearning for Federated Learning Frameworks
231
.FAST:Featureawaresimilaritythresholdingforweakunlearninginblack-box generativemodels
232
Evaluating Inexact Unlearning Requires Revisiting Forgetting
233
Prompt Certified Machine Unlearning with Randomized Gradient Smoothing and Quantization
234
Learning to Refit for Convex Learning Problems
235
Right to Be Forgotten in the Age of Machine Learning
236
Amnesia” - A Selection of Machine Learning Models That Can Forget User Data Very Fast
237
Learning from Failure: De-biasing Classifier from Biased Classifier
238
Protecting personal privacy against unauthorized deep learning models
239
Debunking Misinformation on the Web: Detection, Validation, and Visualisation
240
Predict then Propagate: Combining neural networks with personalized pagerank for classification on graphs
241
A Survey of Learning Causality with Data: Problems and Methods
242
The California consumer privacy act: Towards a Europeanstyle privacy regime in the United States
243
A Public Domain Dataset for Human Activity Recognition using Smartphones
244
DATA LEAKAGE DETECTION USING CLOUD COMPUTING
245
Reading Digits in Natural Images with Unsupervised Feature Learning
246
Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
247
Learning Multiple Layers of Features from Tiny Images
248
Decremental Learning Algorithms for Nonlinear Langrangian and Least Squares Support Vector Machines
249
GradientBased Learning Applied to Document Recognition
250
Incremental and Decremental Support Vector Machine Learning
251
Gradient-based learning applied to document recognition
252
GraphEditor : An Efficient Graph Representation Learning and Unlearning Approach
254
we discuss different designs of machine unlearning, including exact unlearning, approximate unlearning, zero-glance unlearning, zero-shot unlearning, and few-shot unlearning
255
2024. Learning and unlearning to operate profitable secure electric vehicle charging
256
2024. Unlearning with control: Assessing real-world utility for large language model unlearning
257
—Fourth, we introduce a unified taxonomy that categorizes the machine unlearning approaches into three branches: model-agnostic methods, model-intrinsic methods, and data-driven methods
258
2022. Forgetting fast in recommender systems
259
Received 27 September 2024; revised 29 January 2025; accepted 20 June 2025
260
2022.ARCANE:Anefficientarchitectureforexactmachineunlearning
261
2023. GNNDelete: A general strategy for unlearning in graph neural networks
262
2024. Exploring the landscape of machine unlearning: A comprehensive survey and taxonomy
263
2024. SFGCN: Synergetic Fusion-based Graph Convolu-tional Networks Approach for Link Prediction in Social Networks
