SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1702.02284 · 2017

Adversarial Attacks on Neural Network Policies

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1702.02284")
get_code_for_paper("1702.02284")
have("1702.02284")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1702.02284.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1702.02284.svg)](https://syntology.ai/paper/1702.02284)

Connect an agent — have() is free.