.png){kind=icon}
返回
Implementing a Multitarget Backdoor Attack Algorithm Based on Procedural Noise Texture Features
.png){kind=icon}
PRE
AI
DOI：10.1109/ACCESS.2024.3401848.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent studies have shown that deep neural networks (DNNs) may suffer from some security issues such as backdoor attacks. The triggers of backdoor attacks are dynamic and global. However, existing backdoor attack methods are laborious and time-consuming in hiding global triggers, and most of them focus on single-target attacks, with less research on multitarget backdoor attacks. In this work, we present a multitarget attack strategy using texture features of procedural noise. Specifically, we use the k-LSB steganography algorithm to hide the triggers in the image and use different texture features of procedural noise to trigger multiple targets for attack. Poisoned images can be generated more quickly using the k-LSB steganography algorithm without any training process. Multitarget backdoor attacks apply to more scenarios and are more difficult to defend against. We evaluate the effectiveness of the proposed attack method on GTSRB and ImageNet datasets, and the experiments show that the proposed attack can achieve a high attack success rate (up to 100.00% for GTSRB and up to 98.48% for ImageNet) without compromising the clean data's categorization performance, and thus is less likely to arouse the suspicion of administrators. In addition, the attack can bypass existing defense methods (STRIP defense and Neural Cleanse defense).
Keyword:
Noise
Steganography
Training
Artificial neural networks
Perturbation methods
Data models
Lattices
Deep learning
Backdoor attack
deep learning
procedural noise
LSB steganography
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksBadNets: 评估对深度神经网络的后台攻击.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Backdoors hidden in facial features: a novel invisible backdoor attack against face recognition systems隐藏在面部特征中的后门: 针对面部识别系统的新型隐形后门攻击
PREAI
分享收藏分享收藏Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏The triggers that open the NLP model backdoors are hidden in the adversarial samplesCOMPUTERS & SECURITY
COMPUTERS & SECURITYIF5.4
PREAI
分享收藏
查看更多内容