Aniruddha Saha
University of Maryland, Baltimore County
H-index: 7
North America-United States
Top articles of Aniruddha Saha
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
arXiv preprint arXiv:2403.16365
2024/3/25
System and Method with Masking for Certified Defense Against Adversarial Patch Attacks
2024/3/21
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
arXiv preprint arXiv:2401.12070
2024/1/22
A Closer Look at Robustness of Vision Transformers to Backdoor Attacks
2024
NEFTune: Noisy Embeddings Improve Instruction Finetuning
The Twelfth International Conference on Learning Representations (ICLR) 2024
2024
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
arXiv preprint arXiv:2309.00614
2023/9/1
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
arXiv preprint arXiv:2306.13651
2023/6/23
Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
arXiv preprint arXiv:2306.12610
2023/6/22
Aniruddha Saha
H-Index: 4
On the Reliability of Watermarks for Large Language Models
arXiv preprint arXiv:2306.04634
2023/6/7
Backdoor Attacks in Computer Vision: Towards Adversarially Robust Machine Learning Models
2022
Aniruddha Saha
H-Index: 4
Backdoor Attacks on Vision Transformers
arXiv preprint arXiv:2206.08477
2022/6/16
Backdoor Attacks on Self-Supervised Learning
2022
Aniruddha Saha
H-Index: 4
Ajinkya Tejankar
H-Index: 2
Soroush Abbasi Koohpayegani
H-Index: 1
Hamed Pirsiavash
H-Index: 23