Zobrazeno 1 - 10
of 1 028
pro vyhledávání: '"TANG, Di"'
Open source software (OSS) is integral to modern product development, and any vulnerability within it potentially compromises numerous products. While developers strive to apply security patches, pinpointing these patches among extensive OSS updates
Externí odkaz:
http://arxiv.org/abs/2409.06816
Autor:
Wang, Zixuan, Jia, Jia, Sun, Shikun, Wu, Haozhe, Han, Rong, Li, Zhenyu, Tang, Di, Zhou, Jiaqing, Luo, Jiebo
Choreographers determine what the dances look like, while cameramen determine the final presentation of dances. Recently, various methods and datasets have showcased the feasibility of dance synthesis. However, camera movement synthesis with music an
Externí odkaz:
http://arxiv.org/abs/2403.13667
Publikováno v:
NDSS Symposium 2024
Most existing methods to detect backdoored machine learning (ML) models take one of the two approaches: trigger inversion (aka. reverse engineer) and weight analysis (aka. model diagnosis). In particular, the gradient-based trigger inversion is consi
Externí odkaz:
http://arxiv.org/abs/2301.12318
Publikováno v:
44th IEEE Symposium on Security and Privacy, SP 2023, San Francisco, CA, USA, 21-25 May. IEEE, 2023, pp. 1-19
In this paper, we present a simple yet surprisingly effective technique to induce "selective amnesia" on a backdoored model. Our approach, called SEAM, has been inspired by the problem of catastrophic forgetting (CF), a long standing issue in continu
Externí odkaz:
http://arxiv.org/abs/2212.04687
With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect. We believe that answers to these questions
Externí odkaz:
http://arxiv.org/abs/2210.06509
Autor:
Liu, Jiawei, Kang, Yangyang, Tang, Di, Song, Kaisong, Sun, Changlong, Wang, Xiaofeng, Lu, Wei, Liu, Xiaozhong
Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain underexplore
Externí odkaz:
http://arxiv.org/abs/2209.06506
Autor:
Tang, Di-Wei, Chen, I-Chung, Chou, Po-Yu, Lai, Mei-Jung, Liu, Zheng-Yang, Tsai, Kelvin K., Cheng, Li-Hsin, Zhao, Jian-Xun, Cho, Er-Chieh, Chang, Hung-Hsuan, Lin, Tony Eight, Hsu, Kai-Cheng, Chen, Mei-Chuan, Liou, Jing-Ping
Publikováno v:
In European Journal of Medicinal Chemistry 15 November 2024 278
Publikováno v:
In Sustainable Materials and Technologies April 2025 43
Publikováno v:
Fayixue Zazhi, Vol 40, Iss 2, Pp 135-142 (2024)
Objective To investigate the application value of combining the Demirjian’s method with machine learning algorithms for dental age estimation in northern Chinese Han children and adolescents. Methods Oral panoramic images of 10 256 Han individuals
Externí odkaz:
https://doaj.org/article/b25d4f8d17ea4204a6e89d6568032b6c
Autor:
Tang, Di1 (AUTHOR), Ma, Ruisi2 (AUTHOR), Chung, Peichi3 (AUTHOR), Ho, Wai-keung1 (AUTHOR), Sum, Kim-wai Raymond1 (AUTHOR) kwsum@cuhk.edu.hk
Publikováno v:
PLoS ONE. 8/12/2024, Vol. 19 Issue 8, p1-15. 15p.