Timezone: »
Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that initial accuracy is a key aspect of transfer learning performance. In this work, we identify another such aspect: we find that adversarially robust models, while less accurate, often perform better than their standard-trained counterparts when used for transfer learning. Specifically, we focus on adversarially robust ImageNet classifiers, and show that they yield improved accuracy on a standard suite of downstream classification tasks. Further analysis uncovers more differences between robust and standard models in the context of transfer learning. Our results are consistent with (and in fact, add to) recent hypotheses stating that robustness leads to improved feature representations. Code and models is available in the supplementary material.
Author Information
Hadi Salman (Microsoft Research)
Andrew Ilyas (MIT)
Logan Engstrom (MIT)
Ashish Kapoor (Microsoft)
Aleksander Madry (MIT)
Aleksander Madry is the NBX Associate Professor of Computer Science in the MIT EECS Department and a principal investigator in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). He received his PhD from MIT in 2011 and, prior to joining the MIT faculty, he spent some time at Microsoft Research New England and on the faculty of EPFL. Aleksander's research interests span algorithms, continuous optimization, science of deep learning and understanding machine learning from a robustness perspective. His work has been recognized with a number of awards, including an NSF CAREER Award, an Alfred P. Sloan Research Fellowship, an ACM Doctoral Dissertation Award Honorable Mention, and 2018 Presburger Award.
Related Events (a corresponding poster, oral, or spotlight)
-
2020 Poster: Do Adversarially Robust ImageNet Models Transfer Better? »
Wed Dec 9th 05:00 -- 07:00 AM Room Poster Session 2
More from the Same Authors
-
2020 Poster: On Adaptive Attacks to Adversarial Example Defenses »
Florian Tramer · Nicholas Carlini · Wieland Brendel · 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: Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates »
Wenhao Luo · Wen Sun · Ashish Kapoor -
2020 Spotlight: Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificates »
Wenhao Luo · Wen Sun · Ashish Kapoor -
2019 Workshop: Machine Learning with Guarantees »
Ben London · Gintare Karolina Dziugaite · Daniel Roy · Thorsten Joachims · Aleksander Madry · John Shawe-Taylor -
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: Characterizing Bias in Classifiers using Generative Models »
Daniel McDuff · Shuang Ma · Yale Song · Ashish Kapoor -
2019 Poster: Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers »
Hadi Salman · Jerry Li · Ilya Razenshteyn · Pengchuan Zhang · Huan Zhang · Sebastien Bubeck · Greg Yang -
2019 Spotlight: Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers »
Hadi Salman · Jerry Li · Ilya Razenshteyn · Pengchuan Zhang · Huan Zhang · Sebastien Bubeck · Greg Yang -
2019 Poster: Image Synthesis with a Single (Robust) Classifier »
Shibani Santurkar · Andrew Ilyas · Dimitris Tsipras · Logan Engstrom · Brandon Tran · Aleksander Madry -
2019 Poster: Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting »
Aditya Grover · Jiaming Song · Ashish Kapoor · Kenneth Tran · Alekh Agarwal · Eric Horvitz · Stefano Ermon -
2019 Poster: Adversarial Examples Are Not Bugs, They Are Features »
Andrew Ilyas · Shibani Santurkar · Dimitris Tsipras · Logan Engstrom · Brandon Tran · Aleksander Madry -
2019 Spotlight: Adversarial Examples Are Not Bugs, They Are Features »
Andrew Ilyas · Shibani Santurkar · Dimitris Tsipras · Logan Engstrom · Brandon Tran · Aleksander Madry -
2018 Poster: Spectral Signatures in Backdoor Attacks »
Brandon Tran · Jerry Li · Aleksander Madry -
2018 Poster: How Does Batch Normalization Help Optimization? »
Shibani Santurkar · Dimitris Tsipras · Andrew Ilyas · Aleksander Madry -
2018 Poster: Adversarially Robust Generalization Requires More Data »
Ludwig Schmidt · Shibani Santurkar · Dimitris Tsipras · Kunal Talwar · Aleksander Madry -
2018 Oral: How Does Batch Normalization Help Optimization? »
Shibani Santurkar · Dimitris Tsipras · Andrew Ilyas · Aleksander Madry -
2018 Spotlight: Adversarially Robust Generalization Requires More Data »
Ludwig Schmidt · Shibani Santurkar · Dimitris Tsipras · Kunal Talwar · Aleksander Madry -
2018 Tutorial: Adversarial Robustness: Theory and Practice »
J. Zico Kolter · Aleksander Madry -
2016 Poster: Quantum Perceptron Models »
Ashish Kapoor · Nathan Wiebe · Krysta Svore -
2012 Poster: Multilabel Classification using Bayesian Compressed Sensing »
Ashish Kapoor · Raajay Viswanathan · Prateek Jain -
2009 Workshop: Analysis and Design of Algorithms for Interactive Machine Learning »
Sumit Basu · Ashish Kapoor -
2009 Poster: Breaking Boundaries Between Induction Time and Diagnosis Time Active Information Acquisition »
Ashish Kapoor · Eric Horvitz