research
∙
04/30/2021
Stealthy Backdoors as Compression Artifacts
In a backdoor attack on a machine learning model, an adversary produces ...
share
research
∙
06/30/2020
Model-Targeted Poisoning Attacks: Provable Convergence and Certified Bounds
Machine learning systems that rely on training data collected from untru...
research
∙
04/22/2020
Scalable Attack on Graph Data by Injecting Vicious Nodes
Recent studies have shown that graph convolution networks (GCNs) are vul...
research
∙
08/19/2019
Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries
In a black-box setting, the adversary only has API access to the target ...
research
∙
12/23/2017