Obserwuj
Tong Wu
Tong Wu
Princeton University
Zweryfikowany adres z princeton.edu - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Defending against physically realizable attacks on image classification
T Wu, L Tong, Y Vorobeychik
ICLR 2020 Spotlight, 2019
1162019
Adversarial robustness of deep sensor fusion models
S Wang, T Wu, A Chakrabarti, Y Vorobeychik
Proceedings of the IEEE/CVF winter conference on applications of computer …, 2022
24*2022
Privacy-Preserving In-Context Learning for Large Language Models
T Wu, A Panda, J Wang, P Mittal
20*2023
Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
T Wu, T Wang, V Sehwag, S Mahloujifar, P Mittal
AISEC 2022, 2022
202022
Towards A Proactive ML Approach for Detecting Backdoor Poison Samples
X Qi, T Xie, T Wang, T Wu, S Mahloujifar, P Mittal
USENIX 2023, 2023
16*2023
A Randomized Approach for Tight Privacy Accounting
JT Wang, S Mahloujifar, T Wu, R Jia, P Mittal
NeurIPS 2023, 2023
42023
Uncovering Adversarial Risks of Test-Time Adaptation
T Wu, F Jia, X Qi, JT Wang, V Sehwag, S Mahloujifar, P Mittal
ICML 2023, 2023
42023
Can optical trojans assist adversarial perturbations?
A Boloor, T Wu, P Naughton, A Chakrabarti, X Zhang, Y Vorobeychik
Proceedings of the IEEE/CVF International Conference on Computer Vision, 122-131, 2021
32021
Systems and methods for defending against physical attacks on image classification
Y Vorobeychik, T Wu, L Tong
US Patent 20210300433A1, 2021
22021
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses
C Xiang, T Wu, S Dai, J Petit, S Jana, P Mittal
arXiv preprint arXiv:2310.13076, 2023
2023
Short: Certifiably Robust Perception Against Adversarial Patch Attacks: A Survey
C Xiang, C Sitawarin, T Wu, P Mittal
VehicleSec 2023, 2023
2023
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–11