Zobrazeno 1 - 10
of 755
pro vyhledávání: '"Ben Y. Zhao"'
Autor:
Zhujun Xiao, Jenna Cryan, Yuanshun Yao, Yi Hong Gordon Cheo, Yuanchao Shu, Stefan Saroiu, Ben Y. Zhao, Haitao Zheng
Publikováno v:
Proceedings on Privacy Enhancing Technologies. 2023:252-267
Today, face editing is widely used to refine/alter photos in both professional and recreational settings. Yet it is also used to modify (and repost) existing online photos for cyberbullying. Our work considers an important open question: 'How can we
Publikováno v:
IEEE Transactions on Network and Service Management. 18:1775-1788
Today’s video streaming market is crowded with various content providers (CPs). For individual CPs, understanding user behavior, in particular how users migrate among different CPs, is crucial for improving users’ on-site experience and the CP’
Publikováno v:
AISec@CCS
Anonymity systems like Tor are vulnerable to Website Fingerprinting (WF) attacks, where a local passive eavesdropper infers the victim's activity. WF attacks based on deep learning classifiers have successfully overcome numerous defenses. While recen
Autor:
Ben Y. Zhao, Angela Sha, Jenna Cryan, Haitao Zheng, Emily Wenger, Christian Cianfarani, Max Bronckers
Publikováno v:
CCS
Advances in deep learning have introduced a new wave of voice synthesis tools, capable of producing audio that sounds as if spoken by a target speaker. If successful, such tools in the wrong hands will enable a range of powerful attacks against both
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c8e592826d5a6b73588c08a56440859b
http://arxiv.org/abs/2109.09598
http://arxiv.org/abs/2109.09598
Publikováno v:
CHI Extended Abstracts
We propose a novel modality for active biometric authentication: electrical muscle stimulation (EMS). To explore this, we engineered an interactive system, which we call ElectricAuth, that stimulates the user’s forearm muscles with a sequence of el
Publikováno v:
CHI
We propose a novel modality for active biometric authentication: electrical muscle stimulation (EMS). To explore this, we engineered an interactive system, which we call ElectricAuth, that stimulates the user’s forearm muscles with a sequence of el
Autor:
Ben Y. Zhao, Zhilong Chen, Jiaxin Huang, Yong Li, Diyi Yang, Fanchao Meng, Guozhen Zhang, Fengli Xu
Publikováno v:
Proceedings of the ACM on Human-Computer Interaction
Check-in data from social networks provide researchers a unique opportunity to model human dynamics at scale. However, it is unclear how indicative these check-in traces are of real human mobility. Prior work showed that significant amounts of Foursq
Publikováno v:
CCS
Deep neural networks (DNN) are known to be vulnerable to adversarial attacks. Numerous efforts either try to patch weaknesses in trained models, or try to make it difficult or costly to compute adversarial examples that exploit them. In our work, we
Publikováno v:
CIKM
Accurate traffic speed prediction is an important and challenging topic for transportation planning. Previous studies on traffic speed prediction predominately used spatio-temporal and context features for prediction. However, they have not made good
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9c6a8bec236d576abc468d35790ab67d
https://aaltodoc.aalto.fi/handle/123456789/111443
https://aaltodoc.aalto.fi/handle/123456789/111443
Autor:
Josephine Passananti, Ben Y. Zhao, Arjun Nitin Bhagoji, Yuanshun Yao, Haitao Zheng, Emily Wenger
Publikováno v:
CVPR
Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly focus on dig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2581f438ada379a44df3215b4e1f3449
http://arxiv.org/abs/2006.14580
http://arxiv.org/abs/2006.14580