Papers › Concise Explanations of Neural Networks using Adversarial Training

Concise Explanations of Neural Networks using Adversarial Training

15 Oct 2018ICML 2020 1arXiv:1810.06583archive 2025-07-28

Prasad Chalasani, Jiefeng Chen, Amrita Roy Chowdhury, Somesh Jha, Xi Wu

We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions. Two desirable characteristics of an attribution-based explanation are: (1) sparseness: the attributions of irrelevant or weakly relevant features should be negligible, thus resulting in concise explanations in terms of the significant features, and (2) stability: it should not vary significantly within a small local neighborhood of the input. Our first contribution is a theoretical exploration of how these two properties (when using attributions based on Integrated Gradients, or IG) are related to adversarial training, for a class of 1-layer networks (which includes logistic regression models for binary and multi-class classification); for these networks we show that (a) adversarial training using an ℓ_∞-bounded adversary produces models with sparse attribution vectors, and (b) natural model-training while encouraging stable explanations (via an extra term in the loss function), is equivalent to adversarial training. Our second contribution is an empirical verification of phenomenon (a), which we show, somewhat surprisingly, occurs not only in 1-layer networks, but also DNNs trained on standard image datasets, and extends beyond IG-based attributions, to those based on DeepSHAP: adversarial training with ℓ_∞-bounded perturbations yields significantly sparser attribution vectors, with little degradation in performance on natural test data, compared to natural training. Moreover, the sparseness of the attribution vectors is significantly better than that achievable via ℓ₁-regularized natural training.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

jfc43/advex officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-class Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Logistic Regression

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections