Improving Adversarial Robustness of Attribution via Implicit Regularization

• URL: http://arxiv.org/abs/2605.29983v1
• Date: Thu, 28 May 2026 14:19:39 GMT
• Title: Improving Adversarial Robustness of Attribution via Implicit Regularization
• Abstract summary: adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning.<n>We show that robustness can arise implicitly from the learning dynamics of standard gradient descent.<n>Our results highlight learning dynamics as a principled and practical mechanism for robust explainability.
• Score: 9.78455276849371
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this work, we show that attribution robustness can arise implicitly from the learning dynamics of standard stochastic gradient descent. We theoretically motivate this effect through connections between parameter-space and input-space curvature, and validate it across architectures, datasets, and attribution methods, with negligible computational overhead. In contrast, we prove that such robustness gains often does not transfer to attention-based attribution under softmax normalization, due to inherent entropy constraints, and we validate this limitation experimentally. Finally, we show that replacing softmax attention with kernel-based attention restores the robustness gains in transformer models. Our results highlight learning dynamics as a principled and practical mechanism for robust explainability, and reveal fundamental limitations of attention-based attribution under normalization.

Related papers

• Explicit Dropout: Deterministic Regularization for Transformer Architectures [55.09895958546215]
  Dropout is a widely used regularization technique in deep learning, but its effects are typically realized through masking.<n>We propose a deterministic formulation that expresses dropout as an additive regularizer directly incorporated into the training loss.
  arXiv  Detail & Related papers  (2026-04-22T12:45:51Z)
• Transformer Is Inherently a Causal Learner [27.79148022495734]
  We show that transformer trained in an autoregressive manner naturally encodes time-delayed causal structures.<n>We prove this connection theoretically under standard identifiability conditions.<n>This approach greatly surpasses the performance of state-of-the-art discovery algorithms.
  arXiv  Detail & Related papers  (2026-01-09T09:10:04Z)
• Transformers Learn Faster with Semantic Focus [57.97235825738412]
  We study sparse transformers in terms of learnability and generalization.<n>We find that input-dependent sparse attention models appear to converge faster and generalize better than standard attention models.
  arXiv  Detail & Related papers  (2025-06-17T01:19:28Z)
• In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention [52.159541540613915]
  We study how multi-head softmax attention models are trained to perform in-context learning on linear data.<n>Our results reveal that in-context learning ability emerges from the trained transformer as an aggregated effect of its architecture and the underlying data distribution.
  arXiv  Detail & Related papers  (2025-03-17T02:00:49Z)
• Regularization for Adversarial Robust Learning [18.46110328123008]
  We develop a novel approach to adversarial training that integrates $phi$-divergence regularization into the distributionally robust risk function. This regularization brings a notable improvement in computation compared with the original formulation. We validate our proposed method in supervised learning, reinforcement learning, and contextual learning and showcase its state-of-the-art performance against various adversarial attacks.
  arXiv  Detail & Related papers  (2024-08-19T03:15:41Z)
• Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Density [93.32594873253534]
  Trustworthy machine learning requires meticulous regulation of model reliance on non-robust features. We propose a framework to delineate and regulate such features by attributing model predictions to the input.
  arXiv  Detail & Related papers  (2024-07-05T09:16:56Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• Understanding Robust Overfitting from the Feature Generalization Perspective [61.770805867606796]
  Adversarial training (AT) constructs robust neural networks by incorporating adversarial perturbations into natural data. It is plagued by the issue of robust overfitting (RO), which severely damages the model's robustness. In this paper, we investigate RO from a novel feature generalization perspective.
  arXiv  Detail & Related papers  (2023-10-01T07:57:03Z)
• On the Robustness of Removal-Based Feature Attributions [17.679374058425346]
  We theoretically characterize the properties of robustness of removal-based feature attributions. Specifically, we provide a unified analysis of such methods and derive upper bounds for the difference between intact and perturbed attributions. Our results on synthetic and real-world data validate our theoretical results and demonstrate their practical implications.
  arXiv  Detail & Related papers  (2023-06-12T23:33:13Z)
• 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)

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.