Aniruddha Saha

23 papers A* 6A 1Journal 13Unranked 3

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	LLM-Generated Passphrases That Are Secure and Easy to Remember. NAACL (Findings) Jie S. Li, Jonas Geiping, Micah Goldblum, Aniruddha Saha, Tom Goldstein
2024	A	`conf`	A Closer Look at Robustness of Vision Transformers to Backdoor Attacks. WACV Akshayvarun Subramanya, Soroush Abbasi Koohpayegani, Aniruddha Saha, Ajinkya Tejankar, Hamed Pirsiavash
2024	J	`jnl`	Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion. CoRR Hossein Souri, Arpit Bansal, Hamid Kazemi, Liam Fowl, Aniruddha Saha, Jonas Geiping, Andrew Gordon Wilson, Rama Chellappa, Tom Goldstein, Micah Goldblum
2024	A*	`conf`	NEFTune: Noisy Embeddings Improve Instruction Finetuning. ICLR Neel Jain, Ping-Yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2024	A*	`conf`	On the Reliability of Watermarks for Large Language Models. ICLR John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein
2024	A*	`conf`	Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. ICML Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2024	J	`jnl`	Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text. CoRR Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	Baseline Defenses for Adversarial Attacks Against Aligned Language Models. CoRR Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-Yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	Bring Your Own Data! Self-Supervised Evaluation for Large Language Models. CoRR Neel Jain, Khalid Saifullah, Yuxin Wen, John Kirchenbauer, Manli Shu, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	NEFTune: Noisy Embeddings Improve Instruction Finetuning. CoRR Neel Jain, Ping-Yeh Chiang, Yuxin Wen, John Kirchenbauer, Hong-Min Chu, Gowthami Somepalli, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein
2023	J	`jnl`	On the Reliability of Watermarks for Large Language Models. CoRR John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein
2023	J	`jnl`	Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches. CoRR Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh, Wan-Yi Lin, Chaithanya Kumar Mummadi
2023	J	`jnl`	Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches. Trans. Mach. Learn. Res. Aniruddha Saha, Shuhua Yu, Mohammad Sadegh Norouzzadeh, Wan-Yi Lin, Chaithanya Kumar Mummadi
2022	A*	`conf`	Backdoor Attacks on Self-Supervised Learning. CVPR Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
2022	J	`jnl`	Backdoor Attacks on Vision Transformers. CoRR Akshayvarun Subramanya, Aniruddha Saha, Soroush Abbasi Koohpayegani, Ajinkya Tejankar, Hamed Pirsiavash
2021	J	`jnl`	Backdoor Attacks on Self-Supervised Learning. CoRR Aniruddha Saha, Ajinkya Tejankar, Soroush Abbasi Koohpayegani, Hamed Pirsiavash
2020	A*	`conf`	Hidden Trigger Backdoor Attacks. AAAI Aniruddha Saha, Akshayvarun Subramanya, Hamed Pirsiavash
2020	—	`conf`	Role of Spatial Context in Adversarial Robustness for Object Detection. CVPR Workshops Aniruddha Saha, Akshayvarun Subramanya, Koninika Patil, Hamed Pirsiavash
2020	A*	`conf`	Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs. CVPR Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash, Heiko Hoffmann
2019	J	`jnl`	Adversarial Patches Exploiting Contextual Reasoning in Object Detection. CoRR Aniruddha Saha, Akshayvarun Subramanya, Koninika Patil, Hamed Pirsiavash
2019	J	`jnl`	Hidden Trigger Backdoor Attacks. CoRR Aniruddha Saha, Akshayvarun Subramanya, Hamed Pirsiavash
2019	J	`jnl`	Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs. CoRR Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash, Heiko Hoffmann
2016	—	`conf`	An Adaptive Foreground-Background Separation Method for Effective Binarization of Document Images. SoCPaR Bishwadeep Das, Showmik Bhowmik, Aniruddha Saha, Ram Sarkar