Timezone: »
Spotlight
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers
Hadi Salman · Jerry Li · Ilya Razenshteyn · Pengchuan Zhang · Huan Zhang · Sebastien Bubeck · Greg Yang
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ adversarial training to improve the performance of randomized smoothing. We design an adapted attack for smoothed classifiers, and we show how this attack can be used in an adversarial training setting to boost the provable robustness of smoothed classifiers. We demonstrate through extensive experimentation that our method consistently outperforms all existing provably $\ell_2$-robust classifiers by a significant margin on ImageNet and CIFAR-10, establishing the state-of-the-art for provable $\ell_2$-defenses. Moreover, we find that pre-training and semi-supervised learning boost adversarially trained smoothed classifiers even further. Our code and trained models are available at http://github.com/Hadisalman/smoothing-adversarial.
Author Information
Hadi Salman (Microsoft Research AI)
Jerry Li (Microsoft)
Ilya Razenshteyn (Microsoft Research)
Pengchuan Zhang (Microsoft Research)
Huan Zhang (Microsoft Research AI)
Sebastien Bubeck (Microsoft Research)
Greg Yang (Microsoft Research)
Related Events (a corresponding poster, oral, or spotlight)
-
2019 Poster: Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers »
Thu Dec 12th 06:45 -- 08:45 PM Room East Exhibition Hall B + C
More from the Same Authors
-
2020 Poster: Robust Gaussian Covariance Estimation in Nearly-Matrix Multiplication Time »
Jerry Li · Guanghao Ye -
2020 Poster: Do Adversarially Robust ImageNet Models Transfer Better? »
Hadi Salman · Andrew Ilyas · Logan Engstrom · Ashish Kapoor · Aleksander Madry -
2020 Poster: Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing »
Arun Jambulapati · Jerry Li · Kevin Tian -
2020 Spotlight: Robust Sub-Gaussian Principal Component Analysis and Width-Independent Schatten Packing »
Arun Jambulapati · Jerry Li · Kevin Tian -
2020 Oral: Do Adversarially Robust ImageNet Models Transfer Better? »
Hadi Salman · Andrew Ilyas · Logan Engstrom · Ashish Kapoor · Aleksander Madry -
2020 Poster: Denoised Smoothing: A Provable Defense for Pretrained Classifiers »
Hadi Salman · Mingjie Sun · Greg Yang · Ashish Kapoor · J. Zico Kolter -
2020 Poster: Network size and size of the weights in memorization with two-layers neural networks »
Sebastien Bubeck · Ronen Eldan · Yin Tat Lee · Dan Mikulincer -
2020 Poster: Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization »
Sam Hopkins · Jerry Li · Fred Zhang -
2020 Poster: Learning Structured Distributions From Untrusted Batches: Faster and Simpler »
Sitan Chen · Jerry Li · Ankur Moitra -
2019 Poster: A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks »
Hadi Salman · Greg Yang · Huan Zhang · Cho-Jui Hsieh · Pengchuan Zhang -
2019 Poster: Using Statistics to Automate Stochastic Optimization »
Hunter Lang · Lin Xiao · Pengchuan Zhang -
2019 Poster: Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes »
Greg Yang -
2019 Poster: Understanding the Role of Momentum in Stochastic Gradient Methods »
Igor Gitman · Hunter Lang · Pengchuan Zhang · Lin Xiao -
2019 Poster: Complexity of Highly Parallel Non-Smooth Convex Optimization »
Sebastien Bubeck · Qijia Jiang · Yin-Tat Lee · Yuanzhi Li · Aaron Sidford -
2019 Spotlight: Complexity of Highly Parallel Non-Smooth Convex Optimization »
Sebastien Bubeck · Qijia Jiang · Yin-Tat Lee · Yuanzhi Li · Aaron Sidford -
2019 Poster: Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection »
Yihe Dong · Samuel Hopkins · Jerry Li -
2019 Spotlight: Quantum Entropy Scoring for Fast Robust Mean Estimation and Improved Outlier Detection »
Yihe Dong · Samuel Hopkins · Jerry Li -
2018 Poster: Optimal Algorithms for Non-Smooth Distributed Optimization in Networks »
Kevin Scaman · Francis Bach · Sebastien Bubeck · Laurent Massoulié · Yin Tat Lee -
2018 Oral: Optimal Algorithms for Non-Smooth Distributed Optimization in Networks »
Kevin Scaman · Francis Bach · Sebastien Bubeck · Laurent Massoulié · Yin Tat Lee -
2018 Poster: Is Q-Learning Provably Efficient? »
Chi Jin · Zeyuan Allen-Zhu · Sebastien Bubeck · Michael Jordan -
2018 Poster: Turbo Learning for CaptionBot and DrawingBot »
Qiuyuan Huang · Pengchuan Zhang · Dapeng Wu · Lei Zhang -
2017 Poster: Mean Field Residual Networks: On the Edge of Chaos »
Ge Yang · Samuel Schoenholz