Spotlight

Mon 20:38

Information Laundering for Model Privacy
Xinran Wang · Yu Xiang · Jun Gao · Jie Ding

Poster

Tue 17:00

Information Laundering for Model Privacy
Xinran Wang · Yu Xiang · Jun Gao · Jie Ding

Workshop

Boosting black-box adversarial attack via exploiting loss smoothness
Hoang Tran

Workshop

Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
Dequan Wang · David Wagner · Trevor Darrell

Workshop

PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches
Chong Xiang

Poster

Mon 17:00

Robust Reinforcement Learning on State Observations with Learned Optimal Adversary
Huan Zhang · Hongge Chen · Duane S Boning · Cho-Jui Hsieh

Spotlight

Thu 13:30

A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
Sanghyun Hong · Yigitcan Kaya · Ionut-Vlad Modoranu · Tudor Dumitras

Poster

Wed 1:00

A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
Sanghyun Hong · Yigitcan Kaya · Ionut-Vlad Modoranu · Tudor Dumitras

Workshop

Mind the box: $l_1$-APGD for sparse adversarial attacks on image classifiers
francesco croce

Workshop

Detecting Adversarial Attacks through Neural Activations
Graham Annett

Poster

Tue 1:00

Policy-Driven Attack: Learning to Query for Hard-label Black-box Adversarial Examples
Ziang Yan · Yiwen Guo · Jian Liang · Changshui Zhang

Workshop

Fri 9:16

Kendra Albert - Panda v. Gibbon: Legal Liability for Adversarial ML Attacks
Kendra Albert