ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2212.14106
20
0

Provable Robust Saliency-based Explanations

28 December 2022
Chao Chen
Chenghua Guo
Guixiang Ma
Ming Zeng
Xi Zhang
Sihong Xie
    AAML
    FAtt
ArXivPDFHTML
Abstract

Robust explanations of machine learning models are critical to establishing human trust in the models. The top-kkk intersection is widely used to evaluate the robustness of explanations. However, most existing attacking and defense strategies are based on ℓp\ell_pℓp​ norms, thus creating a mismatch between the evaluation and optimization objectives. To this end, we define explanation thickness for measuring top-kkk salient features ranking stability, and design the \textit{R2ET} algorithm based on a novel tractable surrogate to maximize the thickness and stabilize the top salient features efficiently. Theoretically, we prove a connection between R2ET and adversarial training; using a novel multi-objective optimization formulation and a generalization error bound, we further prove that the surrogate objective can improve both the numerical and statistical stability of the explanations. Experiments with a wide spectrum of network architectures and data modalities demonstrate that R2ET attains higher explanation robustness under stealthy attacks while retaining model accuracy.

View on arXiv
Comments on this paper