Urmăriți
Jiawei Kong
Jiawei Kong
Harbin Institute of Technology, Shenzhen
Adresă de e-mail confirmată pe stu.hit.edu.cn
Titlu
Citat de
Citat de
Anul
Privacy leakage on dnns: A survey of model inversion attacks and defenses
H Fang, Y Qiu, H Yu, W Yu, J Kong, B Chong, B Chen, X Wang, ST Xia, ...
arXiv preprint arXiv:2402.04013, 2024
212024
One perturbation is enough: On generating universal adversarial perturbations against vision-language pre-training models
H Fang, J Kong, W Yu, B Chen, J Li, S Xia, K Xu
arXiv preprint arXiv:2406.05491, 2024
102024
Clip-guided generative networks for transferable targeted adversarial attacks
H Fang, J Kong, B Chen, T Dai, H Wu, ST Xia
European Conference on Computer Vision, 1-19, 2024
32024
Neural Antidote: Class-Wise Prompt Tuning for Purifying Backdoors in Pre-trained Vision-Language Models
J Kong, H Fang, S Guo, C Qing, B Chen, B Wang, ST Xia
arXiv preprint arXiv:2502.19269, 2025
2025
Retrievals Can Be Detrimental: A Contrastive Backdoor Attack Paradigm on Retrieval-Augmented Diffusion Models
H Fang, X Sui, H Yu, J Kong, S Yu, B Chen, H Wu, ST Xia
arXiv preprint arXiv:2501.13340, 2025
2025
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–5