Poster

Thu 9:00

Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification
Francisco Utrera · Evan Kravitz · N. Benjamin Erichson · Rajiv Khanna · Michael W Mahoney

Spotlight

Thu 4:35

Unlearnable Examples: Making Personal Data Unexploitable
Hanxun Huang · Xingjun Ma · Sarah Erfani · James Bailey · Yisen Wang

Workshop

Fri 7:12

Poster Spotlight "On Adversarial Robustness: A Neural Architecture Search perspective"
Chaitanya Devaguptapu

Workshop

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

Workshop

FIRM: Detecting Adversarial Audios by Recursive Filters with Randomization
Guanhong Tao

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

Workshop

Measuring Adversarial Robustness using a Voronoi-Epsilon Adversary
Hyeongji Kim

Workshop

Low Curvature Activations Reduce Overfitting in Adversarial Training
Vasu Singla

Poster

Thu 1:00

Certify or Predict: Boosting Certified Robustness with Compositional Architectures
Mark Niklas Müller · Mislav Balunovic · Martin Vechev

Workshop

Fri 12:06

Poster Spotlight "Cost-aware Adversarial Best Arm Identification"
Nikita Ivkin · Valerio Perrone · Giovanni Zappella · Zohar Karnin

Poster

Wed 9:00

Provably robust classification of adversarial examples with detection
Fatemeh Sheikholeslami · Ali Lotfi · Zico Kolter

Poster

Thu 17:00

Learning perturbation sets for robust machine learning
Eric Wong · Zico Kolter