research
∙
07/04/2023
Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction
Machine learning (ML) models are vulnerable to membership inference atta...
share
research
∙
08/11/2021
Turning Your Strength against You: Detecting and Mitigating Robust and Universal Adversarial Patch Attack
Adversarial patch attack against image classification deep neural networ...
research
∙
04/03/2020
TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications
As machine learning (ML) has seen increasing adoption in safety-critical...
research
∙
03/30/2020