# Corrupting Neuron Explanations of Deep Visual Features

arXiv: https://arxiv.org/abs/2310.16332 · HTML: https://mlsanity.com/paper/2310.16332/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 25 Oct 2023.

## Builds on (most cited first, 17 of 17)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Torchattacks: A PyTorch Repository for Adversarial Attacks](https://mlsanity.com/paper/2010.01950/) (2020)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods](https://mlsanity.com/paper/2111.02398/) (2021)
- [Robust Feature-Level Adversaries are Interpretability Tools](https://mlsanity.com/paper/2110.03605/) (2021)
- [Analyzing the Interpretability Robustness of Self-Explaining Models](https://mlsanity.com/paper/1905.12429/) (2019)

## Built on by (most cited first, 2 of 2)

- [The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis](https://mlsanity.com/paper/2408.01416/) (2024)
- [Linear Explanations for Individual Neurons](https://mlsanity.com/paper/2405.06855/) (2024)

## Abstract (arXiv)

The inability of DNNs to explain their black-box behavior has led to a recent surge of explainability methods. However, there are growing concerns that these explainability methods are not robust and trustworthy. In this work, we perform the first robustness analysis of Neuron Explanation Methods under a unified pipeline and show that these explanations can be significantly corrupted by random noises and well-designed perturbations added to their probing data. We find that even adding small random noise with a standard deviation of 0.02 can already change the assigned concepts of up to 28% neurons in the deeper layers. Furthermore, we devise a novel corruption algorithm and show that our algorithm can manipulate the explanation of more than 80% neurons by poisoning less than 10% of probing data. This raises the concern of trusting Neuron Explanation Methods in real-life safety and fairness critical applications.