Sihui Dai

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 17

Top Topics

Computational Efficiency

Episodic Memory

Activation Function

Generative Model

Top Venues

USENIX Security Symposium

Publications

Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aurélie C. Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jirí Navrátil, Soham Dan, Pin-Yu Chen
Larimar: Large Language Models with Episodic Memory Control. CoRR (2024)
Chong Xiang, Tong Wu, Sihui Dai, Jonathan Petit, Suman Jana, Prateek Mittal
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses. USENIX Security Symposium (2024)
Sihui Dai, Chong Xiang, Tong Wu, Prateek Mittal
Position Paper: Beyond Robustness Against Single Attack Types. CoRR (2024)
Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin-Yu Chen, Prateek Mittal
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks. ICML (2023)
Chong Xiang, Tong Wu, Sihui Dai, Jonathan Petit, Suman Jana, Prateek Mittal
PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses. CoRR (2023)
Sihui Dai, Wenxin Ding, Arjun Nitin Bhagoji, Daniel Cullina, Ben Y. Zhao, Haitao Zheng, Prateek Mittal
Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker. CoRR (2023)
Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin-Yu Chen, Prateek Mittal
MultiRobustBench: Benchmarking Robustness Against Multiple Attacks. CoRR (2023)
Sihui Dai, Wenxin Ding, Arjun Nitin Bhagoji, Daniel Cullina, Heather Zheng, Ben Zhao, Prateek Mittal
Characterizing the Optimal 0-1 Loss for Multi-class Classification with a Test-time Attacker. NeurIPS (2023)
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Parameterizing Activation Functions for Adversarial Robustness. SP Workshops (2022)
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Formulating Robustness Against Unforeseen Attacks. NeurIPS (2022)
Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang, Mung Chiang, Prateek Mittal
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness? ICLR (2022)
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Formulating Robustness Against Unforeseen Attacks. CoRR (2022)
Vikash Sehwag, Saeed Mahloujifar, Tinashe Handina, Sihui Dai, Chong Xiang, Mung Chiang, Prateek Mittal
Improving Adversarial Robustness Using Proxy Distributions. CoRR (2021)
Sihui Dai, Saeed Mahloujifar, Prateek Mittal
Parameterizing Activation Functions for Adversarial Robustness. CoRR (2021)
Yujia Huang, James Gornet, Sihui Dai, Zhiding Yu, Tan M. Nguyen, Doris Y. Tsao, Anima Anandkumar
Neural Networks with Recurrent Generative Feedback. CoRR (2020)
Yujia Huang, James Gornet, Sihui Dai, Zhiding Yu, Tan M. Nguyen, Doris Y. Tsao, Anima Anandkumar
Neural Networks with Recurrent Generative Feedback. NeurIPS (2020)
Yujia Huang, Sihui Dai, Tan M. Nguyen, Richard G. Baraniuk, Anima Anandkumar
Out-of-Distribution Detection Using Neural Rendering Generative Models. CoRR (2019)