The code in this repository demonstrates that Deflecting Adversarial Attacks with Pixel Deflection (Prakash et al. 2018) is ineffective in the white-box threat model.

With an L-infinity perturbation of 4/255, we generate targeted adversarial examples with 97% success rate, and can reduce classifier accuracy to 0%.

See our note for more context and details.

Obligatory picture of sample of adversarial examples against this defense.

@unpublished{cvpr2018breaks,
  author = {},
  title = {},
  year = {2018},
url = {https://arxiv.org/abs/TODO},
}