Purify unlearnable examples via rate-constrained variational autoencoders

Purify unlearnable examples via rate-constrained variational autoencoders

Unlearnable examples (UEs) seek to maximize testing error by making subtle modifications to training examples that are correctly labeled. Defenses against these poisoning attacks can be categorized based on whether specific interventions are adopted during training. The first approach is training-ti...

Full description

Bibliographic Details
Main Authors: Yu, Yi, Wang, Yufei, Xia, Song, Yang, Wenhan, Lu, Shijian, Tan, Yap Peng, Kot, Alex Chichung
Other Authors: Interdisciplinary Graduate School (IGS)
Format: Conference Paper
Language:English
Published: 2024
Subjects:
Computer and Information Science
Unlearnable examples
Defense
Poisoning attacks
Indiscriminate poisoning attacks
Purification
Unlearnable datasets
Availibility poisoning attacks
Availibility
Online Access:https://hdl.handle.net/10356/178531
https://proceedings.mlr.press/v235/
https://icml.cc/

Internet

https://hdl.handle.net/10356/178531
https://proceedings.mlr.press/v235/
https://icml.cc/

Similar Items