用标准梯度下降就能提升模型解释的抗干扰能力。
Improving Adversarial Robustness of Attribution via Implicit Regularization
- 利用梯度下降的内在动态实现解释鲁棒性，无需额外计算开销。
- 在多种模型和数据集上验证，解释结果对对抗扰动更稳定。
- 指出注意力机制因归一化限制难以获益，改用核注意力可恢复鲁棒性。
深度学习模型解释的对抗鲁棒性是可靠可解释性的基础要求，但现有方法通常依赖计算成本高昂的显式正则化。本文表明，标准随机梯度下降的学习动态可隐式带来解释鲁棒性。我们通过参数空间与输入空间曲率的关联理论支持这一现象，并在多种架构、数据集和解释方法上验证其有效性，计算开销可忽略不计。相反，我们证明该鲁棒性在使用softmax归一化的注意力机制中往往无法转移，源于固有的熵约束，并通过实验验证了这一局限。最后，我们发现将softmax注意力替换为基于核的注意力，可在Transformer模型中恢复鲁棒性增益。结果凸显学习动态作为稳健可解释性的原理性且实用机制，揭示了归一化下注意力型解释的根本局限。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。