Adversarial Attacks on Neural Network Policies

2017-02-08 · Sandy Huang, Nicolas Papernot, Ian Goodfellow, Yan Duan, Pieter Abbeel

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.

📄 PDF Abstract BibTeX arXiv:1702.02284

Code (1)

ssg-research/ad3-action-distribution-divergence-detector pytorch

Tasks

Reinforcement Learning

Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking

2022-12-10 · Dennis Gross, Thiago D. Simao, Nils Jansen, Guillermo A. Perez

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decre…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents

2020-11-13 · Xian Yeow Lee, Yasaman Esfandiari, Kai Liang Tan, Soumik Sarkar

Advances in computing resources have resulted in the increasing complexity of cyber-physical systems (CPS). As the complexity of CPS evolved, the focus has shifted from traditional control methods to deep reinforcement l…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)Transfer Learning

Adversarial Attacks on Deep Algorithmic Trading Policies

2020-10-22 · Yaser Faghan, Nancirose Piazza, Vahid Behzadan, Ali Fathi

Deep Reinforcement Learning (DRL) has become an appealing solution to algorithmic trading such as high frequency trading of stocks and cyptocurrencies. However, DRL have been shown to be susceptible to adversarial attack…

Algorithmic Trading Deep Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

Delving into adversarial attacks on deep policies

2017-05-18 · Jernej Kos, Dawn Song

Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Attacking and Defending Deep Reinforcement Learning Policies

2022-05-16 · Chao Wang

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a princip…