Explanation-Guided Adversarial Training for Robust and Interpretable Models

• URL: http://arxiv.org/abs/2603.01938v1
• Date: Mon, 02 Mar 2026 14:52:52 GMT
• Title: Explanation-Guided Adversarial Training for Robust and Interpretable Models
• Authors: Chao Chen, Yanhui Chen, Shanshan Lin, Dongsheng Hong, Shu Wu, Xiangwen Liao, Chuanyi Liu,
• Abstract summary: We propose Explanation-Guided Adversarial Training (EGAT) to improve prediction performance, robustness, and explanation quality.<n>EGAT generates adversarial examples on the fly while imposing explanation-based constraints on the model.<n>We show that EGAT consistently outperforms competitive baselines in both clean accuracy and adversarial accuracy +37%.
• Score: 23.590037545621755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep neural networks (DNNs) have achieved remarkable performance in many tasks, yet they often behave as opaque black boxes. Explanation-guided learning (EGL) methods steer DNNs using human-provided explanations or supervision on model attributions. These approaches improve interpretability but typically assume benign inputs and incur heavy annotation costs. In contrast, both predictions and saliency maps of DNNs could dramatically alter facing imperceptible perturbations or unseen patterns. Adversarial training (AT) can substantially improve robustness, but it does not guarantee that model decisions rely on semantically meaningful features. In response, we propose Explanation-Guided Adversarial Training (EGAT), a unified framework that integrates the strength of AT and EGL to simultaneously improve prediction performance, robustness, and explanation quality. EGAT generates adversarial examples on the fly while imposing explanation-based constraints on the model. By jointly optimizing classification performance, adversarial robustness, and attributional stability, EGAT is not only more resistant to unexpected cases, including adversarial attacks and out-of-distribution (OOD) scenarios, but also offer human-interpretable justifications for the decisions. We further formalize EGAT within the Probably Approximately Correct learning framework, demonstrating theoretically that it yields more stable predictions under unexpected situations compared to standard AT. Empirical evaluations on OOD benchmark datasets show that EGAT consistently outperforms competitive baselines in both clean accuracy and adversarial accuracy +37% while producing more semantically meaningful explanations, and requiring only a limited increase +16% in training time.

Related papers

• Spiking Graph Predictive Coding for Reliable OOD Generalization [17.74194220543056]
  We introduce SpIking GrapH predicTive coding (SIGHT), an uncertainty-aware plug-in graph learning module for reliable OOD Generalization.<n>SIGHT performs iterative, error-driven correction over spiking graph states, enabling models to expose internal mismatch signals.
  arXiv  Detail & Related papers  (2026-02-22T23:58:47Z)
• Explainability-Guided Defense: Attribution-Aware Model Refinement Against Adversarial Data Attacks [6.573058520271728]
  We identify a connection between interpretability and robustness that can be directly leveraged during training.<n>We introduce an attribution-guided refinement framework that transforms Local Interpretable Model-Agnostic Explanations into an active training signal.
  arXiv  Detail & Related papers  (2026-01-02T19:36:03Z)
• Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability [0.0]
  Large Language Models (LLMs) show a promising direction and potential for improving domain specific phishing classification tasks.<n>Can LLMs not only classify phishing emails accurately but also generate explanations that are reliably aligned with their predictions and internally self-consistent?<n>We have fine-tuned transformer based models, including BERT, Llama models, and Wizard, to improve domain relevance and make them more tailored to phishing specific distinctions.
  arXiv  Detail & Related papers  (2025-06-16T17:54:28Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off [107.35833747750446]
  adversarial examples can be crafted by adding imperceptible perturbations to legitimate documents. This vulnerability raises significant concerns about their reliability and hinders the widespread deployment of NRMs. In this study, we establish theoretical guarantees regarding the effectiveness-robustness trade-off in NRMs.
  arXiv  Detail & Related papers  (2023-12-16T05:38:39Z)
• Improved and Interpretable Defense to Transferred Adversarial Examples by Jacobian Norm with Selective Input Gradient Regularization [31.516568778193157]
  Adversarial training (AT) is often adopted to improve the robustness of deep neural networks (DNNs) In this work, we propose an approach based on Jacobian norm and Selective Input Gradient Regularization (J- SIGR) Experiments demonstrate that the proposed J- SIGR confers improved robustness against transferred adversarial attacks, and we also show that the predictions from the neural network are easy to interpret.
  arXiv  Detail & Related papers  (2022-07-09T01:06:41Z)
• Latent Boundary-guided Adversarial Training [61.43040235982727]
  Adrial training is proved to be the most effective strategy that injects adversarial examples into model training. We propose a novel adversarial training framework called LAtent bounDary-guided aDvErsarial tRaining.
  arXiv  Detail & Related papers  (2022-06-08T07:40:55Z)
• Robustness and Accuracy Could Be Reconcilable by (Proper) Definition [109.62614226793833]
  The trade-off between robustness and accuracy has been widely studied in the adversarial literature. We find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty.
  arXiv  Detail & Related papers  (2022-02-21T10:36:09Z)
• Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction [11.878012909876713]
  We propose a joint classification and rationale extraction model named AT-BMC. It includes two key mechanisms: mixed Adversarial Training (AT) is designed to use various perturbations in discrete and embedding space to improve the model's robustness, and Boundary Match Constraint (BMC) helps to locate rationales more precisely with the guidance of boundary information. Performances on benchmark datasets demonstrate that the proposed AT-BMC outperforms baselines on both classification and rationale extraction by a large margin.
  arXiv  Detail & Related papers  (2021-12-20T09:48:32Z)
• Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
  Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness. We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
  arXiv  Detail & Related papers  (2020-10-26T04:44:43Z)
• Adversarial Robustness on In- and Out-Distribution Improves Explainability [109.68938066821246]
  RATIO is a training procedure for robustness via Adversarial Training on In- and Out-distribution. RATIO achieves state-of-the-art $l$-adrial on CIFAR10 and maintains better clean accuracy.
  arXiv  Detail & Related papers  (2020-03-20T18:57:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.