firstbacksecondback
13 Results
|
Poster
|
Thu 9:00 |
Detecting Egregious Responses in Neural Sequence-to-sequence Models Tianxing He · James R Glass |
|
|
Poster
|
Tue 14:30 |
Boosting Robustness Certification of Neural Networks Gagandeep Singh · Timon Gehr · Markus Püschel · Martin Vechev |
|
|
Poster
|
Tue 14:30 |
Adversarial Attacks on Graph Neural Networks via Meta Learning Daniel Zügner · Stephan Günnemann |
|
|
Poster
|
Tue 14:30 |
PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks Jan Svoboda · Jonathan Masci · Federico Monti · Michael Bronstein · Leonidas Guibas |
|
|
Poster
|
Tue 14:30 |
Generalizable Adversarial Training via Spectral Normalization Farzan Farnia · Jesse Zhang · David Tse |
|
|
Poster
|
Tue 14:30 |
Defensive Quantization: When Efficiency Meets Robustness Ji Lin · Chuang Gan · Song Han |
|
|
Poster
|
Thu 9:00 |
Complement Objective Training Hao-Yun Chen · Pei-Hsin Wang · Chun-Hao Liu · Shih-Chieh Chang · Jia-Yu Pan · Yu-Ting Chen · Wei Wei · Da-Cheng Juan |
|
|
Poster
|
Tue 14:30 |
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild Yang Zhang · Hassan Foroosh · Phiip David · Boqing Gong |
|
|
Poster
|
Tue 14:30 |
Structured Adversarial Attack: Towards General Implementation and Better Interpretability Kaidi Xu · Sijia Liu · Pu Zhao · Pin-Yu Chen · Huan Zhang · Quanfu Fan · Deniz Erdogmus · Yanzhi Wang · Xue Lin |
|
|
Poster
|
Tue 14:30 |
The Limitations of Adversarial Training and the Blind-Spot Attack Huan Zhang · Hongge Chen · Zhao Song · Duane S Boning · Inderjit Dhillon · Cho-Jui Hsieh |
|
|
Poster
|
Tue 14:30 |
Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors Andrew Ilyas · Logan Engstrom · Aleksander Madry |
|
|
Poster
|
Tue 14:30 |
signSGD via Zeroth-Order Oracle Sijia Liu · Pin-Yu Chen · Xiangyi Chen · Mingyi Hong |