[HTML][HTML] A survey on membership inference attacks and defenses in Machine Learning
Membership inference (MI) attacks mainly aim to infer whether a data record was used to
train a target model or not. Due to the serious privacy risks, MI attacks have been attracting a …
train a target model or not. Due to the serious privacy risks, MI attacks have been attracting a …
Task-aware machine unlearning and its application in load forecasting
Data privacy and security have become a non-negligible factor in load forecasting. Previous
researches mainly focus on training stage enhancement. However, once the model is …
researches mainly focus on training stage enhancement. However, once the model is …
Machine Unlearning by Suppressing Sample Contribution
X Cheng, Z Huang, X Huang - arXiv preprint arXiv:2402.15109, 2024 - arxiv.org
Machine Unlearning (MU) is to forget data from a well-trained model, which is practically
important due to the" right to be forgotten". In this paper, we start from the fundamental …
important due to the" right to be forgotten". In this paper, we start from the fundamental …
MU-Bench: A Multitask Multimodal Benchmark for Machine Unlearning
Recent advancements in Machine Unlearning (MU) have introduced solutions to selectively
remove certain training samples, such as those with outdated or sensitive information, from …
remove certain training samples, such as those with outdated or sensitive information, from …
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
The advent of Federated Learning (FL) highlights the practical necessity for the'right to be
forgotten'for all clients, allowing them to request data deletion from the machine learning …
forgotten'for all clients, allowing them to request data deletion from the machine learning …
One-Shot Unlearning of Personal Identities
Machine unlearning (MU) aims to erase data from a model as if it never saw them during
training. To this extent, existing MU approaches assume complete or partial access to the …
training. To this extent, existing MU approaches assume complete or partial access to the …
[PDF][PDF] MultiDelete for Multimodal Machine Unlearning
J Cheng, H Amiri - arXiv preprint arXiv:2311.12047, 2023 - clu.cs.uml.edu
Machine Unlearning removes specific knowledge about training data samples from an
already trained model. It has significant practical benefits, such as purging private …
already trained model. It has significant practical benefits, such as purging private …