# Erratum Concerning the Obfuscated Gradients Attack on Stochastic Activation Pruning

arXiv: https://arxiv.org/abs/2010.00071 · HTML: https://mlsanity.com/paper/2010.00071/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2020.

## Built on by (most cited first, 1 of 1)

- [Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective](https://mlsanity.com/paper/2311.01047/) (2023)

## Abstract (arXiv)

Stochastic Activation Pruning (SAP) (Dhillon et al., 2018) is a defense to adversarial examples that was attacked and found to be broken by the "Obfuscated Gradients" paper (Athalye et al., 2018). We discover a flaw in the re-implementation that artificially weakens SAP. When SAP is applied properly, the proposed attack is not effective. However, we show that a new use of the BPDA attack technique can still reduce the accuracy of SAP to 0.1%.