Toggle Poster Visibility
Oral
Thu Jul 22 07:00 PM -- 07:20 PM (PDT)
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
[ Paper ]
Spotlight
Thu Jul 22 07:20 PM -- 07:25 PM (PDT)
Towards Defending against Adversarial Examples via Attack-Invariant Features
[ Paper ]
Spotlight
Thu Jul 22 07:25 PM -- 07:30 PM (PDT)
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
[ Paper ]
Spotlight
Thu Jul 22 07:30 PM -- 07:35 PM (PDT)
Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
[ Paper ]
Spotlight
Thu Jul 22 07:35 PM -- 07:40 PM (PDT)
Improving Gradient Regularization using Complex-Valued Neural Networks
[ Paper ]
Spotlight
Thu Jul 22 07:40 PM -- 07:45 PM (PDT)
Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference
[ Paper ]
Spotlight
Thu Jul 22 07:45 PM -- 07:50 PM (PDT)
Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation
[ Paper ]