Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
Adversarial Attacks on Neural Network Policies
lib:9f16a4f4cb99f9a8 (v1.0.0)
Authors: Sandy Huang,Nicolas Papernot,Ian Goodfellow,Yan Duan,Pieter Abbeel
ArXiv: 1702.02284
Document: PDF DOI
Abstract URL: http://arxiv.org/abs/1702.02284v1
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural network policies in reinforcement learning. Specifically, we show existing adversarial example crafting techniques can be used to significantly degrade test-time performance of trained policies. Our threat model considers adversaries capable of introducing small perturbations to the raw input of the policy. We characterize the degree of vulnerability across tasks and training algorithms, for a subclass of adversarial-example attacks in white-box and black-box settings. Regardless of the learned task or training algorithm, we observe a significant drop in performance, even with small adversarial perturbations that do not interfere with human perception. Videos are available at http://rll.berkeley.edu/adversarial.
ArXiv: 1702.02284
Document: PDF DOI
Abstract URL: http://arxiv.org/abs/1702.02284v1
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural network policies in reinforcement learning. Specifically, we show existing adversarial example crafting techniques can be used to significantly degrade test-time performance of trained policies. Our threat model considers adversaries capable of introducing small perturbations to the raw input of the policy. We characterize the degree of vulnerability across tasks and training algorithms, for a subclass of adversarial-example attacks in white-box and black-box settings. Regardless of the learned task or training algorithm, we observe a significant drop in performance, even with small adversarial perturbations that do not interfere with human perception. Videos are available at http://rll.berkeley.edu/adversarial.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)