Improving attribution through transferable adversarial attacks

doi:10.1016/j.patcog.2026.114496

Improving attribution through transferable adversarial attacks

2026-07-01

0

PRE

AI

CHEN Fang (Fang Chen) *

DOI：10.1016/j.patcog.2026.114496

Original

Original request for help

Save

Abstract

En 中文

The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision. In this paper, we propose AttEXplore+, a unified adversarial attribution framework built upon AttEXplore that connects transferable adversarial exploration with gradient-path attribution. Rather than treating transferable attacks merely as additional attack choices, AttEXplore+ reformulates them as gradient acquisition operators for constructing smoother and more structured decision-boundary exploration paths. We instantiate AttEXplore++ with validated operators such as MIG and GRA, and conduct extensive experiments on five models, including CNNs (Inception-v3, ResNet-50, VGG16) and vision transformers (MaxViT-T, ViT-B/16), using the ImageNet dataset. Our method achieves an average performance improvement of 7.57% over AttEXplore and 32.62% compared to other state-of-the-art interpretability algorithms. Using insertion and deletion scores as evaluation metrics, we show that adversarial transferability plays a vital role in enhancing attribution results. Furthermore, we explore the impact of randomness, perturbation rate, noise amplitude, and diversity probability on attribution performance, demonstrating that AttEXplore++ provides more stable and reliable explanations across various models. We release our code at: https://github.com/KxPlaug/ATTEXPLOREP.

Keywords:

Interpretability

Transferable adversarial attack

Explainable AI

Attribution

Improving attribution through transferable adversarial attacks

Abstract

Journal

Organization

Cited Papers