# Massif: Interactive Interpretation of Adversarial Attacks on Deep Learning

arXiv: https://arxiv.org/abs/2001.07769 · HTML: https://mlsanity.com/paper/2001.07769/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 4 of 4)

- [NeuroCartography: Scalable Automatic Visual Summarization of Concepts in Deep Neural Networks](https://mlsanity.com/paper/2108.12931/) (2021)
- [Interactive Machine Learning: A State of the Art Review](https://mlsanity.com/paper/2207.06196/) (2022)
- [EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry](https://mlsanity.com/paper/2103.08820/) (2021)
- [SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models](https://mlsanity.com/paper/2101.10586/) (2021)

## Abstract (arXiv)

Deep neural networks (DNNs) are increasingly powering high-stakes applications such as autonomous cars and healthcare; however, DNNs are often treated as "black boxes" in such applications. Recent research has also revealed that DNNs are highly vulnerable to adversarial attacks, raising serious concerns over deploying DNNs in the real world. To overcome these deficiencies, we are developing Massif, an interactive tool for deciphering adversarial attacks. Massif identifies and interactively visualizes neurons and their connections inside a DNN that are strongly activated or suppressed by an adversarial attack. Massif provides both a high-level, interpretable overview of the effect of an attack on a DNN, and a low-level, detailed description of the affected neurons. These tightly coupled views in Massif help people better understand which input features are most vulnerable or important for correct predictions.