Robustness

Sign-OPT: Defending the hard-label black-box cyber attack

SenSR: the first practical algorithm for individual fairness

Fast and efficient black-box testing for AI cybersecurity

Adversarial Robustness vs Model Compression, or Both?

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method

A content-aware attack generator for AI cybersecurity

ZO-AdaMM: Derivative-free optimization for black-box problems

Defensive Quantization: When Efficiency Meets Robustness

Deep Leakage from Gradients

Tight Certificates of Adversarial Robustness

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

Neural Network Robustness Certification with General Activation Functions

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks

signSGD via Zeroth-Order Oracle

Structured Adversarial Attack: Towards General Implementation and Better Interpretability

AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks

Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning