Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability

2025/09/25 by Yavari, Ali, Mohamadi, Alireza, Beydaghi, Elham +1
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2510.03245

Abstract

Ensuring the reliability of deep neural networks (DNNs) in the presence of real world noise and intentional perturbations remains a significant challenge. To address this, attribution methods have been proposed, though their efficacy remains suboptimal and necessitates further refinement. In this paper, we propose a novel category of transferable adversarial attacks, called transferable frequency-aware attacks, enabling frequency-aware exploration via both high-and low-frequency components. Based on this type of attacks, we also propose a novel attribution method, named Frequency-Aware Model Parameter Explorer (FAMPE), which improves the explainability for DNNs. Relative to the current state-of-the-art method AttEXplore, our FAMPE attains an average gain of 13.02% in Insertion Score, thereby outperforming existing approaches. Through detailed ablation studies, we also investigate the role of both high- and low-frequency components in explainability.

Citations

• Explainable AI for Mental Disorder Detection via Social Media: A survey and outlook
• MFABA: A More Faithful and Accelerated Boundary-based Attribution Method for Deep Neural Networks
• MaxViT: Multi-Axis Vision Transformer
• Fast Axiomatic Attribution for Neural Networks
• Robust Models Are More Interpretable Because Attributions Look Normal
• Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
• A Fourier Perspective on Model Robustness in Computer Vision
• High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
• Low Frequency Adversarial Perturbation
• RISE: Randomized Input Sampling for Explanation of Black-box Models
• A Deep Causal Inference Approach to Measuring the Effects of Forming Group Loans in Online Non-profit Microfinance Platform
• Axiomatic Attribution for Deep Networks
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
• Layer-wise Relevance Propagation for Neural Networks with Local\n Renormalization Layers
• Deep Residual Learning for Image Recognition
• Rethinking the Inception Architecture for Computer Vision
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• An algorithm for the machine calculation of complex Fourier series

Related

• Don't FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
• Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability
• Attribution for Enhanced Explanation with Transferable Adversarial eXploration
• Improving Adversarial Transferability via Neuron Attribution-Based Attacks
• FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks