Reinforcement Learning Based Black-Box Adversarial Attack for Robustness Improvement

强化学习 计算机科学 对抗制 稳健性(进化) 人工智能 机器学习 均方误差 模式识别(心理学) 数学 生物化学 基因 统计 化学
作者
Soumyendu Sarkar,Ashwin Ramesh Babu,Sajad Mousavi,Sahand Ghorbanpour,Vineet Gundecha,Ricardo Luna Gutiérrez,Antonio Guillén,Avisek Naug
标识
DOI:10.1109/case56687.2023.10260607
摘要

We propose a Reinforcement Learning (RL) based adversarial Black-box attack (RLAB) that aims at adding minimum distortion to the input iteratively to deceive image classification models. The RL agent learns to identify highly sensitive regions in the input's feature space to add distortions to induce misclassification with minimum steps and L2 norm. The agent also selectively removes noises introduced at earlier steps in the iteration, which has less impact on the model at a given state. This novel dual-action method is equivalent to doing a deep tree search to add noises without an exhaustive search, leading to the faster generation of an optimum adversarial sample. This black-box method focuses on naturally occurring distortion to effectively measure the robustness of models, a key element of trustworthiness. The proposed method beats existing heuristic based state-of-the-art black-box adversarial attacks on metrics such as the number of queries, L2 norm, and success rate on ImageNet and CIFAR-10 datasets. For the ImageNet dataset, the average number of queries achieved by the proposed method for ResNet-50, Inception-V3, and VGG-16 models are 42%, 32%, and 31 % better than the popular "Square Attack". Furthermore, retraining the model with adversarial samples significantly improved robustness when evaluated on benchmark datasets such as CIFAR-10-C with the metrics of adversarial error and mean corruption error (mCE). Demo: https://tinyurl.com/yr8f7x9t
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
111111完成签到,获得积分10
1秒前
西西发布了新的文献求助10
1秒前
1秒前
hongfangpan关注了科研通微信公众号
1秒前
偷乐发布了新的文献求助10
1秒前
田様应助独特凡松采纳,获得10
2秒前
wwwwww发布了新的文献求助10
4秒前
lyting发布了新的文献求助10
4秒前
4秒前
crane完成签到,获得积分10
5秒前
Hello应助Rosie采纳,获得10
5秒前
小陈要发一区完成签到,获得积分10
5秒前
药毛儿发布了新的文献求助10
7秒前
llll完成签到,获得积分10
7秒前
7秒前
木木完成签到,获得积分10
8秒前
情怀应助loski采纳,获得10
9秒前
田様应助专注的乐荷采纳,获得10
9秒前
9秒前
9秒前
10秒前
小蘑菇应助无奈秋荷采纳,获得10
12秒前
到处找帮手的刘完成签到,获得积分10
13秒前
13秒前
NexusExplorer应助俏皮的白柏采纳,获得10
15秒前
15秒前
科目三应助药毛儿采纳,获得10
17秒前
egg发布了新的文献求助10
17秒前
lyting完成签到,获得积分10
17秒前
阿萨德完成签到,获得积分10
17秒前
万能图书馆应助多多采纳,获得10
18秒前
风起完成签到 ,获得积分10
18秒前
wwwwww完成签到,获得积分10
18秒前
量子星尘发布了新的文献求助10
19秒前
无花果应助好好采纳,获得10
19秒前
19秒前
xyx945应助创新采纳,获得10
21秒前
22秒前
23秒前
情怀应助madefu采纳,获得10
24秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3988827
求助须知:如何正确求助?哪些是违规求助? 3531197
关于积分的说明 11252739
捐赠科研通 3269830
什么是DOI,文献DOI怎么找? 1804815
邀请新用户注册赠送积分活动 881915
科研通“疑难数据库(出版商)”最低求助积分说明 809028