An Extension of Fano's Inequality for Characterizing Model Susceptibility to Membership Inference Attacks

no code implementations • 17 Sep 2020 • Sumit Kumar Jha, Susmit Jha, Rickard Ewetz, Sunny Raj, Alvaro Velasquez, Laura L. Pullum, Ananthram Swami

We present a new extension of Fano's inequality and employ it to theoretically establish that the probability of success for a membership inference attack on a deep neural network can be bounded using the mutual information between its inputs and its activations.

Inference Attack Membership Inference Attack

Attribution-Based Confidence Metric For Deep Neural Networks

1 code implementation • NeurIPS 2019 • Susmit Jha, Sunny Raj, Steven Fernandes, Sumit K. Jha, Somesh Jha, Brian Jalaian, Gunjan Verma, Ananthram Swami

These experiments demonstrate the effectiveness of the ABC metric to make DNNs more trustworthy and resilient.

Attribution-driven Causal Analysis for Detection of Adversarial Examples

no code implementations • 14 Mar 2019 • Susmit Jha, Sunny Raj, Steven Lawrence Fernandes, Sumit Kumar Jha, Somesh Jha, Gunjan Verma, Brian Jalaian, Ananthram Swami

We study the robustness of machine learning models on benign and adversarial inputs in this neighborhood.

Adversarial Attack BIG-bench Machine Learning