Vikash Sehwag
Princeton University
H-index: 15
North America-United States
Top articles of Vikash Sehwag
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
arXiv preprint arXiv:2404.01318
2024/3/28
Finding needles in a haystack: A Black-Box Approach to Invisible Watermark Detection
arXiv preprint arXiv:2403.15955
2024/3/23
Differentially private image classification by learning priors from random processes
Advances in Neural Information Processing Systems
2024/2/13
Scaling Compute Is Not All You Need for Adversarial Robustness
International Conference on Learning Representations (ICLR) Workshop on Reliable and Responsible Foundation Models
2023/12/20
Edoardo Debenedetti
H-Index: 0
Zishen Wan
H-Index: 4
Maksym Andriushchenko
H-Index: 9
Vikash Sehwag
H-Index: 7
A New Linear Scaling Rule for Differentially Private Hyperparameter Optimization
2023/12/12
Multirobustbench: Benchmarking robustness against multiple attacks
2023/7/3
Sihui Dai
H-Index: 2
Saeed Mahloujifar
H-Index: 8
Chong Xiang
H-Index: 3
Vikash Sehwag
H-Index: 7
Prateek Mittal
H-Index: 34
Differentially Private Generation of High Fidelity Samples From Diffusion Models
2023/6/23
A light recipe to train robust vision transformers
2023/2/8
Uncovering adversarial risks of test-time adaptation
International Conference on Machine Learning (ICML), 2023
2023/1/29
Tong Wu
H-Index: 8
Xiangyu Qi
H-Index: 1
Vikash Sehwag
H-Index: 7
Saeed Mahloujifar
H-Index: 8
Prateek Mittal
H-Index: 34
Promises and Pitfalls of Generative AI: An AI-Safety Centric Approach
2023
Vikash Sehwag
H-Index: 7
Extracting training data from diffusion models
arXiv preprint arXiv:2301.13188
2023/1/30
Dp-raft: A differentially private recipe for accelerated fine-tuning
arXiv preprint arXiv:2212.04486
2022/12/8
Understanding robust learning through the lens of representation similarities
2022/6/20
Just rotate it: Deploying backdoor attacks via rotation transformation
2022/11/11
Tong Wu
H-Index: 8
Tianhao Wang
H-Index: 4
Vikash Sehwag
H-Index: 7
Saeed Mahloujifar
H-Index: 8
Prateek Mittal
H-Index: 34
Generating high fidelity data from low-density regions using diffusion models
2022
Vikash Sehwag
H-Index: 7
Beyond Norms: Delving Deeper into Robustness to Physical Image Transformations
2021/11/29
Vikash Sehwag
H-Index: 7
Lower bounds on cross-entropy loss in the presence of test-time adversaries
2021/7/1
Arjun Nitin Bhagoji
H-Index: 10
Daniel Cullina
H-Index: 12
Vikash Sehwag
H-Index: 7
Prateek Mittal
H-Index: 34
Robust learning meets generative models: Can proxy distributions improve adversarial robustness?
2022
Ssd: A unified framework for self-supervised outlier detection
arXiv preprint arXiv:2103.12051
2021/3/22
{PatchGuard}: A provably robust defense against adversarial patches via small receptive fields and masking
2021