Papers Machine Unlearning
“Machine Unlearning” 태그가 달린 논문 438편 · 필터 해제
Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning
Privacy concerns in machine learning are heightened by regulations such as the GDPR, which enforces the "right to be forgotten" (RTBF), driving the emergence of machine unlearning as a critical research field. Vertical F…
Federated LearningMachine UnlearningVertical Federated LearningWhen to Forget? Complexity Trade-offs in Machine Unlearning
Machine Unlearning (MU) aims at removing the influence of specific data points from a trained model, striving to achieve this at a fraction of the cost of full model retraining. In this paper, we analyze the efficiency o…
Machine UnlearningOn the Vulnerability of Concept Erasure in Diffusion Models
The proliferation of text-to-image diffusion models has raised significant privacy and security concerns, particularly regarding the generation of copyrighted or harmful images. In response, several concept erasure (defe…
Machine UnlearningExploring Incremental Unlearning: Techniques, Challenges, and Future Directions
The growing demand for data privacy in Machine Learning (ML) applications has seen Machine Unlearning (MU) emerge as a critical area of research. As the `right to be forgotten' becomes regulated globally, it is increasin…
Machine UnlearningPrivacy PreservingA Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a principled approach to removing the influence …
Machine UnlearningSoft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models
Large language models (LLMs) have become increasingly popular. Their emergent capabilities can be attributed to their massive training datasets. However, these datasets often contain undesirable or inappropriate content,…
Machine UnlearningSafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific knowledge in training dat…
Machine UnlearningVisual Question Answering (VQA)ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
Backdoor attacks embed hidden functionalities in deep neural networks (DNN), triggering malicious behavior with specific inputs. Advanced defenses monitor anomalous DNN inferences to detect such attacks. However, conceal…
Backdoor AttackMachine UnlearningMMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models
Recent progress in Machine Unlearning (MU) has introduced solutions for the selective removal of private or sensitive information encoded within deep neural networks. Nonetheless, MU for Multimodal Large Language Models …
Language ModelingLanguage ModellingMachine UnlearningVisual Question Answering (VQA)Privacy Preservation through Practical Machine Unlearning
Machine Learning models thrive on vast datasets, continuously adapting to provide accurate predictions and recommendations. However, in an era dominated by privacy concerns, Machine Unlearning emerges as a transformative…
Machine UnlearningPartially Labeled DatasetsComparative Study of Machine Unlearning Techniques for Computer Vision and NLP Models
Machine unlearning is an emerging field in machine learning that focuses on efficiently removing the influence of specific data from a trained model. This capability is critical in scenarios requiring compliance with dat…
Machine UnlearningSEMU: Singular Value Decomposition for Efficient Machine Unlearning
While the capabilities of generative foundational models have advanced rapidly in recent years, methods to prevent harmful and unsafe behaviors remain underdeveloped. Among the pressing challenges in AI safety, machine u…
Machine UnlearningMitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning
Large Language Models for Code (LLMs4Code) excel at code generation tasks, yielding promise to release developers from huge software development burdens. Nonetheless, these models have been shown to suffer from the signi…
Code GenerationMachine UnlearningMemorizationMachine Unlearning via Information Theoretic Regularization
How can we effectively remove or "unlearn" undesirable information, such as specific features or individual data points, from a learning outcome while minimizing utility loss and ensuring rigorous guarantees? We introduc…
Machine UnlearningRealistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention
Machine Unlearning allows participants to remove their data from a trained machine learning model in order to preserve their privacy, and security. However, the machine unlearning literature for generative models is rath…
Machine UnlearningFALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model
Large language models have been widely applied, but can inadvertently encode sensitive or harmful information, raising significant safety concerns. Machine unlearning has emerged to alleviate this concern; however, exist…
Language ModelingLanguage ModellingLarge Language ModelMachine UnlearningRedefining Machine Unlearning: A Conformal Prediction-Motivated Approach
Machine unlearning seeks to remove the influence of specified data from a trained model. While metrics such as unlearning accuracy (UA) and membership inference attack (MIA) provide baselines for assessing unlearning per…
Adversarial AttackConformal Predictionimage-classificationImage Classification+5SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders
Diffusion models, while powerful, can inadvertently generate harmful or undesirable content, raising significant ethical and safety concerns. Recent machine unlearning approaches offer potential solutions but often lack …
Adversarial AttackDenoisingfeature selectionMachine UnlearningData Duplication: A Novel Multi-Purpose Attack Paradigm in Machine Unlearning
Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However,…
Machine UnlearningFUNU: Boosting Machine Unlearning Efficiency by Filtering Unnecessary Unlearning
Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and cor…
Machine UnlearningMemorization