Improving transferable adversarial attack via feature-momentum

对抗制 计算机科学 特征(语言学) 可转让性 边距(机器学习) 钥匙(锁) 机器学习 人工智能 数据挖掘 计算机安全 语言学 哲学 罗伊特
作者
Xianglong He,Yuezun Li,Haipeng Qu,Junyu Dong
出处
期刊:Computers & Security [Elsevier BV]
卷期号:128: 103135-103135 被引量:9
标识
DOI:10.1016/j.cose.2023.103135
摘要

Transferable adversarial attackusing adversarial perturbations made on known models to attack unknown modelshas made significant progress in recent years. The feature-level adversarial approach, in particular, is one of the most common solutions and can improve transferability by disrupting intermediate features, regardless of the task-specific loss objectives. Once the intermediate features are disrupted, the subsequent prediction will naturally go wrong. To accomplish this, the existing methods often start an attack by creating a guidance map on features that shows the importance level of each feature element, and then they use an iterative strategy to disrupt the features based on the guidance map. However, the drawback of existing methods is that the guidance map is always fixed in iterations, which can not consistently reflect the importance of feature elements, limiting the performance of the attack consequently. In this paper, we describe a new method called Feature-Momentum Adversarial Attack (FMAA) to enhance transferability. The key idea is that we estimate a guidance map dynamically at each iteration using a momentum-style approach to effectively disturb the features. Extensive experiments demonstrate that our method significantly outperforms other state-of-the-art methods by a large margin on different target models.
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
沉默网络完成签到 ,获得积分10
刚刚
科目三应助动听幻儿采纳,获得10
1秒前
2秒前
2秒前
3秒前
ldjack发布了新的文献求助10
6秒前
123456发布了新的文献求助10
6秒前
十一发布了新的文献求助10
7秒前
yanyifan完成签到,获得积分10
7秒前
盖世英雄完成签到,获得积分10
8秒前
8秒前
9秒前
欢呼吐司完成签到,获得积分10
10秒前
xiaoqi发布了新的文献求助10
10秒前
10秒前
12秒前
12秒前
chufan完成签到,获得积分10
13秒前
Bio应助Yurrrrt采纳,获得50
13秒前
13秒前
13秒前
miki完成签到,获得积分10
13秒前
13秒前
Hesse发布了新的文献求助10
14秒前
16秒前
Ava应助chufan采纳,获得10
16秒前
打打应助yuhang采纳,获得10
17秒前
17秒前
睿籽发布了新的文献求助10
18秒前
19秒前
19秒前
Eve发布了新的文献求助10
20秒前
xiaoqi完成签到,获得积分10
22秒前
爆米花应助失眠的莫英采纳,获得10
22秒前
22秒前
Eunhyo发布了新的文献求助10
23秒前
今后应助甜美的秋尽采纳,获得10
23秒前
oleskarabach发布了新的文献求助10
24秒前
Jennie完成签到,获得积分20
28秒前
斯文败类应助萌酱采纳,获得10
28秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
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 3975250
求助须知:如何正确求助?哪些是违规求助? 3519625
关于积分的说明 11199055
捐赠科研通 3255962
什么是DOI,文献DOI怎么找? 1798001
邀请新用户注册赠送积分活动 877358
科研通“疑难数据库(出版商)”最低求助积分说明 806298