Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Zhaoyang, Wu, Zhihao, Lu, Wang, Gao, Xin, Yue, Jinghang, Zhang, Taolin, Wang, Lipo, Lin, Youfang, Wang, Jing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.01168
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913816249368576
author Ma, Zhaoyang
Wu, Zhihao
Lu, Wang
Gao, Xin
Yue, Jinghang
Zhang, Taolin
Wang, Lipo
Lin, Youfang
Wang, Jing
author_facet Ma, Zhaoyang
Wu, Zhihao
Lu, Wang
Gao, Xin
Yue, Jinghang
Zhang, Taolin
Wang, Lipo
Lin, Youfang
Wang, Jing
contents The development of model ensemble attacks has significantly improved the transferability of adversarial examples, but this progress also poses severe threats to the security of deep neural networks. Existing methods, however, face two critical challenges: insufficient capture of shared gradient directions across models and a lack of adaptive weight allocation mechanisms. To address these issues, we propose a novel method Harmonized Ensemble for Adversarial Transferability (HEAT), which introduces domain generalization into adversarial example generation for the first time. HEAT consists of two key modules: Consensus Gradient Direction Synthesizer, which uses Singular Value Decomposition to synthesize shared gradient directions; and Dual-Harmony Weight Orchestrator which dynamically balances intra-domain coherence, stabilizing gradients within individual models, and inter-domain diversity, enhancing transferability across models. Experimental results demonstrate that HEAT significantly outperforms existing methods across various datasets and settings, offering a new perspective and direction for adversarial attack research.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01168
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Harmonizing Intra-coherence and Inter-divergence in Ensemble Attacks for Adversarial Transferability
Ma, Zhaoyang
Wu, Zhihao
Lu, Wang
Gao, Xin
Yue, Jinghang
Zhang, Taolin
Wang, Lipo
Lin, Youfang
Wang, Jing
Machine Learning
Artificial Intelligence
The development of model ensemble attacks has significantly improved the transferability of adversarial examples, but this progress also poses severe threats to the security of deep neural networks. Existing methods, however, face two critical challenges: insufficient capture of shared gradient directions across models and a lack of adaptive weight allocation mechanisms. To address these issues, we propose a novel method Harmonized Ensemble for Adversarial Transferability (HEAT), which introduces domain generalization into adversarial example generation for the first time. HEAT consists of two key modules: Consensus Gradient Direction Synthesizer, which uses Singular Value Decomposition to synthesize shared gradient directions; and Dual-Harmony Weight Orchestrator which dynamically balances intra-domain coherence, stabilizing gradients within individual models, and inter-domain diversity, enhancing transferability across models. Experimental results demonstrate that HEAT significantly outperforms existing methods across various datasets and settings, offering a new perspective and direction for adversarial attack research.
title Harmonizing Intra-coherence and Inter-divergence in Ensemble Attacks for Adversarial Transferability
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2505.01168