Results 21 to 30 of about 1,236,597 (154)
Diffusion Models for Imperceptible and Transferable Adversarial Attack [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Many existing adversarial attacks generate $L_{p}$Lp-norm perturbations on image RGB space. Despite some achievements in transferability and attack success rate, the crafted adversarial examples are easily perceived by human eyes.
Jianqi Chen +5 more
semanticscholar +1 more source
A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion [PDF]
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023 Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study the problem of adversarial attack generation for Stable Diffusion and ask
Haomin Zhuang, Yihua Zhang, Sijia Liu
semanticscholar +1 more source
BERT-ATTACK: Adversarial Attack against BERT Using BERT [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 Adversarial attacks for discrete data (such as text) has been proved significantly more challenging than continuous data (such as image), since it is difficult to generate adversarial samples with gradient-based methods.
Linyang Li +4 more
semanticscholar +1 more source
Generalizable Black-Box Adversarial Attack With Meta Learning [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget.
Fei Yin +6 more
semanticscholar +1 more source
EIFDAA: Evaluation of an IDS with function-discarding adversarial attacks in the IIoT
Heliyon, 2023 The complexity of the Industrial Internet of Things (IIoT) presents higher requirements for intrusion detection systems (IDSs). An adversarial attack is a threat to the security of machine learning-based IDSs.
Shiming Li +4 more
doaj +1 more source
Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity [PDF]
Computer Vision and Pattern Recognition, 2022 Current adversarial attack research reveals the vulnerability of learning-based classifiers against carefully crafted perturbations. However, most existing attack methods have inherent limitations in cross-dataset generalization as they rely on a ...
Cheng Luo +5 more
semanticscholar +1 more source
On the Reversibility of Adversarial Attacks
2021 IEEE International Conference on Image Processing (ICIP), 2021 Adversarial attacks modify images with perturbations that change the prediction of classifiers. These modified images, known as adversarial examples, expose the vulnerabilities of deep neural network classifiers. In this paper, we investigate the predictability of the mapping between the classes predicted for original images and for their corresponding
Chau Yi Li +4 more
openaire +2 more sources
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon [PDF]
Computer Vision and Pattern Recognition, 2022 Estimating the risk level of adversarial examples is essential for safely deploying machine learning models in the real world. One popular approach for physical-world attacks is to adopt the “sticker-pasting” strategy, which however suffers from some ...
Yiqi Zhong +4 more
semanticscholar +1 more source
Adversarial Attacks on Adversarial Bandits
CoRR, 2023 Accepted by ICLR ...
Yuzhe Ma, Zhijin Zhou
openaire +3 more sources
A Survey on Universal Adversarial Attack [PDF]
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021 The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single perturbation to fool the target DNN for most images.
Chaoning Zhang +5 more
openaire +2 more sources