Skip to content
conftrace_

dirty-label attack

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor poisoning attacks (1) effectiveness (1) theoretical insights (1) two-layer convolutional neural network (1) clean-label attack (1) membership inference (1) privacy leakage (1) convolutional neural network (1) adversarial attack (1) transfer learning (1)

Papers

A Theoretical Analysis of Backdoor Poisoning Attacks in Convolutional Neural Networks ICML 2024 Amplifying Membership Exposure via Data Poisoning NeurIPS 2022