1 code implementation • 4 Jul 2023 • Zitao Chen, Karthik Pattabiraman
Machine learning (ML) models are vulnerable to membership inference attacks (MIAs), which determine whether a given input is used for training the target model.
1 code implementation • 11 Aug 2021 • Zitao Chen, Pritam Dash, Karthik Pattabiraman
Therefore, Jujutsu leverages generative adversarial networks (GAN) to perform localized attack recovery by synthesizing the semantic contents of the input that are corrupted by the attacks, and reconstructs a ``clean'' input for correct prediction.
1 code implementation • 3 Apr 2020 • Zitao Chen, Niranjhana Narayanan, Bo Fang, Guanpeng Li, Karthik Pattabiraman, Nathan DeBardeleben
TensorFI is a configurable FI tool that is flexible, easy to use, and portable.
no code implementations • 30 Mar 2020 • Zitao Chen, Guanpeng Li, Karthik Pattabiraman
The adoption of deep neural networks (DNNs) in safety-critical domains has engendered serious reliability concerns.