{
  "id": "1705.06452",
  "version": "v1",
  "published": "2017-05-18T08:01:53.000Z",
  "updated": "2017-05-18T08:01:53.000Z",
  "title": "Delving into adversarial attacks on deep policies",
  "authors": [
    "Jernej Kos",
    "Dawn Song"
  ],
  "comment": "ICLR 2017 Workshop",
  "categories": [
    "stat.ML",
    "cs.LG"
  ],
  "abstract": "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. In this paper we present a novel study into adversarial attacks on deep reinforcement learning polices. We compare the effectiveness of the attacks using adversarial examples vs. random noise. We present a novel method for reducing the number of times adversarial examples need to be injected for a successful attack, based on the value function. We further explore how re-training on random noise and FGSM perturbations affects the resilience against adversarial examples.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-05-18T08:01:53.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "adversarial attacks",
      "deep policies",
      "random noise",
      "times adversarial examples",
      "deep reinforcement learning polices"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}