Enhancing the Transferability of Adversarial Attacks via Multi-Feature Attention

对抗制 计算机科学 可转让性 特征(语言学) 计算机安全 特征提取 人工智能 模式识别(心理学) 数据挖掘 机器学习 语言学 哲学 罗伊特
作者
Desheng Zheng,Wuping Ke,Xiaoyu Li,Yaoxin Duan,Guangqiang Yin,Fan Min
出处
期刊:IEEE Transactions on Information Forensics and Security [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tifs.2025.3526067
摘要

Adversarial examples have posed a serious threat to deep neural networks due to their transferability. Existing transfer-based attacks tend to improve the transferability of adversarial examples by destroying intrinsic features. However, prior work typically employed single-dimensional or additive importance estimates, which provide inaccurate representations of features. In this work, we propose the Multi-Feature Attention Attack (MFAA), which fuses multiple layers of feature representations to disrupt category-related features and thus improve the transferability of the adversarial examples. First, MFAA introduces a layer-aggregation gradient (LAG) to obtain guidance maps, which reflect the importance of features in multiple scales. Second, it generates ensemble attention (EA), preserving object-specific features and offsetting model-specific features based on the guidance maps. Third, EA is iteratively disturbed to achieve high transferability of the adversarial examples. Empirical evaluation on the standard ImageNet dataset shows that adversarial examples crafted by MFAA can effectively attack different networks. Compared to the state-of-the-art transferable attacks, our attack improves the average attack success rate of the black-box model with defense from 88.5% to 94.1% on single-model attacks and from 86.6% to 95.1% on ensemble attacks. Our code is available at Github: https://github.com/KWPCCC/MFAA.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
思源应助大方弘文采纳,获得30
1秒前
杜欣发布了新的文献求助10
1秒前
2秒前
UltraLuo发布了新的文献求助10
2秒前
5秒前
6秒前
玖文完成签到,获得积分10
7秒前
今后应助文献一搜就出采纳,获得10
7秒前
开心采白完成签到 ,获得积分10
7秒前
7秒前
张叮当完成签到,获得积分10
8秒前
8秒前
liu完成签到,获得积分10
10秒前
acffo完成签到 ,获得积分10
11秒前
小雨发布了新的文献求助10
12秒前
lqllll发布了新的文献求助10
12秒前
14秒前
17秒前
风清扬发布了新的文献求助10
19秒前
量子星尘发布了新的文献求助10
20秒前
20秒前
xiaosuda75发布了新的文献求助10
20秒前
20秒前
20秒前
FashionBoy应助小龙虾采纳,获得10
21秒前
JenifferF完成签到,获得积分10
21秒前
大唐元给大唐元的求助进行了留言
21秒前
卡卡西应助老10采纳,获得20
22秒前
欢呼白晴完成签到 ,获得积分10
22秒前
慕青应助鳗鱼友灵采纳,获得10
23秒前
23秒前
dong应助ayuelei采纳,获得10
23秒前
SYLH应助无私的芹采纳,获得10
24秒前
24秒前
希望天下0贩的0应助lqllll采纳,获得30
25秒前
Damon发布了新的文献求助10
28秒前
爆米花应助hao采纳,获得10
29秒前
30秒前
mr完成签到 ,获得积分10
32秒前
ty发布了新的文献求助20
32秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969557
求助须知:如何正确求助?哪些是违规求助? 3514377
关于积分的说明 11173836
捐赠科研通 3249692
什么是DOI,文献DOI怎么找? 1794979
邀请新用户注册赠送积分活动 875537
科研通“疑难数据库(出版商)”最低求助积分说明 804836