| Hidden Trigger Backdoor Attacks A Saha, A Subramanya, H Pirsiavash Proceedings of the AAAI Conference on Artificial Intelligence 2020, 2020 | 874 | 2020 |
| Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs S Kolouri, A Saha, H Pirsiavash, H Hoffmann Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 | 306 | 2020 |
| Baseline Defenses for Adversarial Attacks Against Aligned Language Models N Jain, A Schwarzschild, Y Wen, G Somepalli, J Kirchenbauer, P Chiang, ... arXiv preprint arXiv:2309.00614, 2023 | 219 | 2023 |
| On the Reliability of Watermarks for Large Language Models J Kirchenbauer, J Geiping, Y Wen, M Shu, K Saifullah, K Kong, ... The Twelfth International Conference on Learning Representations (ICLR) 2024, 2024 | 201 | 2024 |
| Backdoor Attacks on Self-Supervised Learning A Saha, A Tejankar, SA Koohpayegani, H Pirsiavash Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 160 | 2022 |
| Role of Spatial Context in Adversarial Robustness for Object Detection A Saha, A Subramanya, K Patil, H Pirsiavash Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020 | 99* | 2020 |
| NEFTune: Noisy Embeddings Improve Instruction Finetuning N Jain, P Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ... The Twelfth International Conference on Learning Representations (ICLR) 2024, 2024 | 95 | 2024 |
| Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text A Hans, A Schwarzschild, V Cherepanova, H Kazemi, A Saha, ... Forty-first International Conference on Machine Learning (ICML) 2024, 2024 | 90 | 2024 |
| A Closer Look at Robustness of Vision Transformers to Backdoor Attacks A Subramanya, SA Koohpayegani, A Saha, A Tejankar, H Pirsiavash Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2024 | 43* | 2024 |
| Bring Your Own Data! Self-Sensitivity Evaluation for Large Language Models N Jain, K Saifullah, Y Wen, J Kirchenbauer, M Shu, A Saha, M Goldblum, ... First Conference on Language Modeling (COLM) 2024, 2024 | 36* | 2024 |
| An Adaptive Foreground-Background Separation Method for Effective Binarization of Document Images B Das, S Bhowmik, A Saha, R Sarkar Proceedings of the Eighth International Conference on Soft Computing and …, 2017 | 8 | 2017 |
| Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches A Saha, S Yu, A Norouzzadeh, WY Lin, CK Mummadi Transactions on Machine Learning Research (TMLR), 2023 | 7 | 2023 |
| Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion H Souri, A Bansal, H Kazemi, L Fowl, A Saha, J Geiping, AG Wilson, ... ICML 2024 Workshop on the Next Generation of AI Safety, 2024 | 2 | 2024 |
| System and method with masking for certified defenses against adversarial patches CK Mummadi, WY Lin, F CONDESSA, A Saha, S Yu US Patent 12,400,006, 2025 | | 2025 |
| System and method with masking and inpainting strategy for generic defense against patch attacks A Saha, CK Mummadi, WY Lin, F CONDESSA US Patent 12,394,028, 2025 | | 2025 |
| LLM-Generated Passphrases That Are Secure and Easy to Remember JS Li, J Geiping, M Goldblum, A Saha, T Goldstein Findings of the Association for Computational Linguistics: NAACL 2025, 5216-5234, 2025 | | 2025 |
| System and method with masking for certified defense against adversarial patch attacks S Yu, A Saha, CK Mummadi, WY Lin US Patent 12,236,695, 2025 | | 2025 |
| System and Method with Multi-Size Masking for Certified Defenses Against Adversarial Patches CK Mummadi, W Lin, F Condessa, A Saha, S Yu US Patent App. 18/332,385, 2024 | | 2024 |
| Backdoor Attacks in Computer Vision: Towards Adversarially Robust Machine Learning Models A Saha University of Maryland, Baltimore County, 2022 | | 2022 |
Hamed PirsiavashAssociate Professor at University of California, DavisVerified email at ucdavis.edu
