Harsh Chaudhari

31 papers A* 6Journal 22Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Identifying Models Behind Text-to-Image Leaderboards. CoRR Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari, Alina Oprea, Amir Houmansadr
2026	J	`jnl`	Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models. CoRR Harsh Chaudhari, Ethan Rathbun, Hanna Foerster, Jamie Hayes, Matthew Jagielski, Milad Nasr, Ilia Shumailov, Alina Oprea
2025	A*	`conf`	Cascading Adversarial Bias from Injection to Distillation in Language Models. CCS Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea
2025	J	`jnl`	Cascading Adversarial Bias from Injection to Distillation in Language Models. CoRR Harsh Chaudhari, Jamie Hayes, Matthew Jagielski, Ilia Shumailov, Milad Nasr, Alina Oprea
2025	J	`jnl`	Exploiting Leaderboards for Large-Scale Distribution of Malicious Models. CoRR Anshuman Suri, Harsh Chaudhari, Yuefeng Peng, Ali Naseh, Amir Houmansadr, Alina Oprea
2025	—	`conf`	Measuring memorization in language models via probabilistic extraction. NAACL (Long Papers) Jamie Hayes, Marika Swanberg, Harsh Chaudhari, Itay Yona, Ilia Shumailov, Milad Nasr, Christopher A. Choquette-Choo, Katherine Lee, A. Feder Cooper
2025	J	`jnl`	R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model. CoRR Ali Naseh, Harsh Chaudhari, Jaechul Roh, Mingshi Wu, Alina Oprea, Amir Houmansadr
2025	J	`jnl`	Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated. CoRR Hanna Foerster, Ilia Shumailov, Yiren Zhao, Harsh Chaudhari, Jamie Hayes, Robert Mullins, Yarin Gal
2025	A*	`conf`	Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation. CCS Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari, Alina Oprea, Amir Houmansadr
2025	J	`jnl`	Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation. CoRR Ali Naseh, Yuefeng Peng, Anshuman Suri, Harsh Chaudhari, Alina Oprea, Amir Houmansadr
2025	J	`jnl`	Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security. CoRR Ali Naseh, Anshuman Suri, Yuefeng Peng, Harsh Chaudhari, Alina Oprea, Amir Houmansadr
2025	J	`jnl`	The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections. CoRR Milad Nasr, Nicholas Carlini, Chawin Sitawarin, Sander V. Schulhoff, Jamie Hayes, Michael Ilie, Juliette Pluto, Shuang Song, Harsh Chaudhari, Ilia Shumailov, Abhradeep Thakurta, Kai Yuanqing Xiao, Andreas Terzis, Florian Tramèr
2024	A*	`conf`	Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning. ICLR Harsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan R. Ullman
2024	J	`jnl`	L3Cube-MahaSocialNER: A Social Media based Marathi NER Dataset and BERT models. CoRR Harsh Chaudhari, Anuja Patil, Dhanashree Lavekar, Pranav Khairnar, Raviraj Joshi
2024	J	`jnl`	Measuring memorization through probabilistic discoverable extraction. CoRR Jamie Hayes, Marika Swanberg, Harsh Chaudhari, Itay Yona, Ilia Shumailov
2024	J	`jnl`	Phantom: General Trigger Attacks on Retrieval Augmented Language Generation. CoRR Harsh Chaudhari, Giorgio Severi, John Abascal, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea
2024	J	`jnl`	UTrace: Poisoning Forensics for Private Collaborative Learning. CoRR Evan Rose, Hidde Lycklama, Harsh Chaudhari, Anwar Hithnawi, Alina Oprea
2023	J	`jnl`	Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning. CoRR Harsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan R. Ullman
2023	J	`jnl`	On Significance of Subword tokenization for Low Resource and Efficient Named Entity Recognition: A case study in Marathi. CoRR Harsh Chaudhari, Anuja Patil, Dhanashree Lavekar, Pranav Khairnar, Raviraj Joshi, Sachin Pande
2023	A*	`conf`	SNAP: Efficient Extraction of Private Properties with Poisoning. SP Harsh Chaudhari, John Abascal, Alina Oprea, Matthew Jagielski, Florian Tramèr, Jonathan R. Ullman
2023	—	`conf`	SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning. SaTML Harsh Chaudhari, Matthew Jagielski, Alina Oprea
2022	J	`jnl`	SNAP: Efficient Extraction of Private Properties with Poisoning. CoRR Harsh Chaudhari, John Abascal, Alina Oprea, Matthew Jagielski, Florian Tramèr, Jonathan R. Ullman
2022	J	`jnl`	SafeNet: Mitigating Data Poisoning Attacks on Private Machine Learning. CoRR Harsh Chaudhari, Matthew Jagielski, Alina Oprea
2022	J	`jnl`	SafeNet: Mitigating Data Poisoning Attacks on Private Machine Learning. IACR Cryptol. ePrint Arch. Harsh Chaudhari, Matthew Jagielski, Alina Oprea
2020	A*	`conf`	Data Poisoning Attacks against Differentially Private Recommender Systems. SIGIR Soumya Wadhwa, Saurabh Agrawal, Harsh Chaudhari, Deepthi Sharma, Kannan Achan
2020	J	`jnl`	FLASH: Fast and Robust Framework for Privacy-preserving Machine Learning. Proc. Priv. Enhancing Technol. Megha Byali, Harsh Chaudhari, Arpita Patra, Ajith Suresh
2020	A*	`conf`	Trident: Efficient 4PC Framework for Privacy Preserving Machine Learning. NDSS Harsh Chaudhari, Rahul Rachuri, Ajith Suresh
2019	—	`conf`	ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction. CCSW Harsh Chaudhari, Ashish Choudhury, Arpita Patra, Ajith Suresh
2019	J	`jnl`	ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction. CoRR Harsh Chaudhari, Ashish Choudhury, Arpita Patra, Ajith Suresh
2019	J	`jnl`	ASTRA: High Throughput 3PC over Rings with Application to Secure Prediction. IACR Cryptol. ePrint Arch. Harsh Chaudhari, Ashish Choudhury, Arpita Patra, Ajith Suresh
2019	J	`jnl`	FLASH: Fast and Robust Framework for Privacy-preserving Machine Learning. IACR Cryptol. ePrint Arch. Megha Byali, Harsh Chaudhari, Arpita Patra, Ajith Suresh