Alert button
Picture for Vikash Sehwag

Vikash Sehwag

Alert button

Scaling Compute Is Not All You Need for Adversarial Robustness

Dec 20, 2023
Edoardo Debenedetti, Zishen Wan, Maksym Andriushchenko, Vikash Sehwag, Kshitij Bhardwaj, Bhavya Kailkhura

Viaarxiv icon

Differentially Private Image Classification by Learning Priors from Random Processes

Jun 08, 2023
Xinyu Tang, Ashwinee Panda, Vikash Sehwag, Prateek Mittal

Figure 1 for Differentially Private Image Classification by Learning Priors from Random Processes
Figure 2 for Differentially Private Image Classification by Learning Priors from Random Processes
Figure 3 for Differentially Private Image Classification by Learning Priors from Random Processes
Figure 4 for Differentially Private Image Classification by Learning Priors from Random Processes
Viaarxiv icon

MultiRobustBench: Benchmarking Robustness Against Multiple Attacks

Feb 21, 2023
Sihui Dai, Saeed Mahloujifar, Chong Xiang, Vikash Sehwag, Pin-Yu Chen, Prateek Mittal

Figure 1 for MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Figure 2 for MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Figure 3 for MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Figure 4 for MultiRobustBench: Benchmarking Robustness Against Multiple Attacks
Viaarxiv icon

Uncovering Adversarial Risks of Test-Time Adaptation

Feb 04, 2023
Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal

Figure 1 for Uncovering Adversarial Risks of Test-Time Adaptation
Figure 2 for Uncovering Adversarial Risks of Test-Time Adaptation
Figure 3 for Uncovering Adversarial Risks of Test-Time Adaptation
Figure 4 for Uncovering Adversarial Risks of Test-Time Adaptation
Viaarxiv icon

Extracting Training Data from Diffusion Models

Jan 30, 2023
Nicholas Carlini, Jamie Hayes, Milad Nasr, Matthew Jagielski, Vikash Sehwag, Florian Tramèr, Borja Balle, Daphne Ippolito, Eric Wallace

Figure 1 for Extracting Training Data from Diffusion Models
Figure 2 for Extracting Training Data from Diffusion Models
Figure 3 for Extracting Training Data from Diffusion Models
Figure 4 for Extracting Training Data from Diffusion Models
Viaarxiv icon

DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning

Dec 15, 2022
Ashwinee Panda, Xinyu Tang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal

Figure 1 for DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning
Figure 2 for DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning
Figure 3 for DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning
Figure 4 for DP-RAFT: A Differentially Private Recipe for Accelerated Fine-Tuning
Viaarxiv icon

A Light Recipe to Train Robust Vision Transformers

Sep 15, 2022
Edoardo Debenedetti, Vikash Sehwag, Prateek Mittal

Figure 1 for A Light Recipe to Train Robust Vision Transformers
Figure 2 for A Light Recipe to Train Robust Vision Transformers
Figure 3 for A Light Recipe to Train Robust Vision Transformers
Figure 4 for A Light Recipe to Train Robust Vision Transformers
Viaarxiv icon

Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation

Jul 22, 2022
Tong Wu, Tianhao Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal

Figure 1 for Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Figure 2 for Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Figure 3 for Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Figure 4 for Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation
Viaarxiv icon