Varun Chandrasekaran

75 papers A* 15A 2B 1Misc 1Journal 47Unranked 9

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Challenges in Enabling Private Data Valuation. CoRR Yiwei Fu, Tianhao Wang, Varun Chandrasekaran
2026	J	`jnl`	Layer-Targeted Multilingual Knowledge Erasure in Large Language Models. CoRR Taoran Li, Varun Chandrasekaran, Zhiyuan Yu
2026	J	`jnl`	Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models. CoRR Xiangwen Wang, Ananth Balashankar, Varun Chandrasekaran
2025	J	`jnl`	AMUN: Adversarial Machine UNlearning. CoRR Ali Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran
2025	J	`jnl`	Analyzing Security and Privacy Challenges in Generative AI Usage Guidelines for Higher Education. CoRR Bei Yi Ng, Jiarui Li, Xinyuan Tong, Kevin Ye, Gauthami Yenne, Varun Chandrasekaran, Jingjie Li
2025	—	`conf`	Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models. ACL (1) Rishabh Adiga, Besmira Nushi, Varun Chandrasekaran
2025	J	`jnl`	D2RA: Dual Domain Regeneration Attack. CoRR Pragati Shuddhodhan Meshram, Varun Chandrasekaran
2025	J	`jnl`	Efficiently Attacking Memorization Scores. CoRR Tue Do, Varun Chandrasekaran, Daniel Alabi
2025	A*	`conf`	Generative Monoculture in Large Language Models. ICLR Fan Wu, Emily Black, Varun Chandrasekaran
2025	J	`jnl`	LLM-Driven Multi-step Translation from C to Rust using Static Analysis. CoRR Tianyang Zhou, Haowen Lin, Somesh Jha, Mihai Christodorescu, Kirill Levchenko, Varun Chandrasekaran
2025	J	`jnl`	MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation. CoRR Siddharth Joshi, Besmira Nushi, Vidhisha Balachandran, Varun Chandrasekaran, Vibhav Vineet, Neel Joshi, Baharan Mirzasoleiman
2025	J	`jnl`	MM-GEN: Principled and Generalizable Data Curation for Enhancing Task Performance in VLMs. J. Data-centric Mach. Learn. Res. Siddharth Joshi, Besmira Nushi, Vidhisha Balachandran, Varun Chandrasekaran, Vibhav Vineet, Neel Joshi, Baharan Mirzasoleiman
2025	A*	`conf`	Not All Wrong is Bad: Using Adversarial Examples for Unlearning. ICML Ali Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran
2025	J	`jnl`	SoK: Understanding (New) Security Issues Across AI4Code Use Cases. CoRR Qilong Wu, Taoran Li, Tianyang Zhou, Varun Chandrasekaran
2025	J	`jnl`	The Erasure Illusion: Stress-Testing the Generalization of LLM Forgetting Evaluation. CoRR Hengrui Jia, Taoran Li, Jonas Guan, Varun Chandrasekaran
2025	Misc	`conf`	The Privacy Quagmire: Where Computer Scientists and Lawyers May Disagree. HotNets Yunwei Zhao, Varun Chandrasekaran, Thomas Wies, Lakshminarayanan Subramanian
2025	A*	`conf`	Training Robust Ensembles Requires Rethinking Lipschitz Continuity. ICLR Ali Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran
2025	A*	`conf`	Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models. ICLR Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet
2025	—	`conf`	Verifiable and Provably Secure Machine Unlearning. SaTML Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran, Esha Ghosh, Olga Ohrimenko, Nicolas Papernot
2024	A*	`conf`	Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models. ICLR Mert Yüksekgönül, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi
2024	J	`jnl`	Attention Speaks Volumes: Localizing and Mitigating Bias in Language Models. CoRR Rishabh Adiga, Besmira Nushi, Varun Chandrasekaran
2024	J	`jnl`	BENCHAGENTS: Automated Benchmark Creation with Agent Interaction. CoRR Natasha Butt, Varun Chandrasekaran, Neel Joshi, Besmira Nushi, Vidhisha Balachandran
2024	—	`conf`	Bypassing LLM Watermarks with Color-Aware Substitutions. ACL (1) Qilong Wu, Varun Chandrasekaran
2024	J	`jnl`	Bypassing LLM Watermarks with Color-Aware Substitutions. CoRR Qilong Wu, Varun Chandrasekaran
2024	—	`conf`	Designing Informative Metrics for Few-Shot Example Selection. ACL (Findings) Rishabh Adiga, Lakshmi Subramanian, Varun Chandrasekaran
2024	J	`jnl`	Designing Informative Metrics for Few-Shot Example Selection. CoRR Rishabh Adiga, Lakshminarayanan Subramanian, Varun Chandrasekaran
2024	J	`jnl`	Generative Monoculture in Large Language Models. CoRR Fan Wu, Emily Black, Varun Chandrasekaran
2024	B	`conf`	Hierarchical Federated Learning with Privacy. IEEE Big Data Varun Chandrasekaran, Suman Banerjee, Diego Perino, Nicolas Kourtellis
2024	A*	`conf`	KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval. ICLR Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yüksekgönül, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi
2024	J	`jnl`	LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles. CoRR Ali Ebrahimpour Boroojeny, Hari Sundaram, Varun Chandrasekaran
2024	A*	`conf`	Privately Aligning Language Models with Reinforcement Learning. ICLR Fan Wu, Huseyin A. Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim
2024	A*	`conf`	Teaching Language Models to Hallucinate Less with Synthetic Tasks. ICLR Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Hassan Awadallah, Ece Kamar
2024	J	`jnl`	The Efficacy of Transfer-based No-box Attacks on Image Watermarking: A Pragmatic Analysis. CoRR Qilong Wu, Varun Chandrasekaran
2024	J	`jnl`	Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models. CoRR Mazda Moayeri, Vidhisha Balachandran, Varun Chandrasekaran, Safoora Yousefi, Thomas Fel, Soheil Feizi, Besmira Nushi, Neel Joshi, Vibhav Vineet
2023	J	`jnl`	Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models. CoRR Mert Yüksekgönül, Varun Chandrasekaran, Erik Jones, Suriya Gunasekar, Ranjita Naik, Hamid Palangi, Ece Kamar, Besmira Nushi
2023	J	`jnl`	Diversity of Thought Improves Reasoning Abilities of Large Language Models. CoRR Ranjita Naik, Varun Chandrasekaran, Mert Yüksekgönül, Hamid Palangi, Besmira Nushi
2023	J	`jnl`	KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval. CoRR Marah I Abdin, Suriya Gunasekar, Varun Chandrasekaran, Jerry Li, Mert Yüksekgönül, Rahee Ghosh Peshawaria, Ranjita Naik, Besmira Nushi
2023	J	`jnl`	Privately Aligning Language Models with Reinforcement Learning. CoRR Fan Wu, Huseyin A. Inan, Arturs Backurs, Varun Chandrasekaran, Janardhan Kulkarni, Robert Sim
2023	A	`conf`	Proof-of-Learning is Currently More Broken Than You Think. EuroS&P Congyu Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot
2023	J	`jnl`	Sparks of Artificial General Intelligence: Early experiments with GPT-4. CoRR Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott M. Lundberg, Harsha Nori, Hamid Palangi, Marco Túlio Ribeiro, Yi Zhang
2023	J	`jnl`	Teaching Language Models to Hallucinate Less with Synthetic Tasks. CoRR Erik Jones, Hamid Palangi, Clarisse Simões, Varun Chandrasekaran, Subhabrata Mukherjee, Arindam Mitra, Ahmed Awadallah, Ece Kamar
2023	J	`jnl`	Why Train More? Effective and Efficient Membership Inference via Memorization. CoRR Jihye Choi, Shruti Tople, Varun Chandrasekaran, Somesh Jha
2022	A*	`conf`	CONFIDANT: A Privacy Controller for Social Robots. HRI Brian Tang, Dakota Sullivan, Bengisu Cagiltay, Varun Chandrasekaran, Kassem Fawaz, Bilge Mutlu
2022	J	`jnl`	CONFIDANT: A Privacy Controller for Social Robots. CoRR Brian Tang, Dakota Sullivan, Bengisu Cagiltay, Varun Chandrasekaran, Kassem Fawaz, Bilge Mutlu
2022	J	`jnl`	Generative Extraction of Audio Classifiers for Speaker Identification. CoRR Tejumade Afonja, Lucas Bourtoule, Varun Chandrasekaran, Sageev Oore, Nicolas Papernot
2022	J	`jnl`	Hierarchical Federated Learning with Privacy. CoRR Varun Chandrasekaran, Suman Banerjee, Diego Perino, Nicolas Kourtellis
2022	J	`jnl`	On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning. CoRR Congyu Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Varun Chandrasekaran, Nicolas Papernot
2022	A	`conf`	Unrolling SGD: Understanding Factors Influencing Machine Unlearning. EuroS&P Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, Nicolas Papernot
2022	J	`jnl`	Verifiable and Provably Secure Machine Unlearning. CoRR Thorsten Eisenhofer, Doreen Riepel, Varun Chandrasekaran, Esha Ghosh, Olga Ohrimenko, Nicolas Papernot
2021	A*	`conf`	A General Framework For Detecting Anomalous Inputs to DNN Classifiers. ICML Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha, Suman Banerjee
2021	J	`jnl`	Causally Constrained Data Synthesis for Private Data Release. CoRR Varun Chandrasekaran, Darren Edge, Somesh Jha, Amit Sharma, Cheng Zhang, Shruti Tople
2021	A*	`conf`	Entangled Watermarks as a Defense against Model Extraction. USENIX Security Symposium Hengrui Jia, Christopher A. Choquette-Choo, Varun Chandrasekaran, Nicolas Papernot
2021	J	`jnl`	Face-Off: Adversarial Face Obfuscation. Proc. Priv. Enhancing Technol. Varun Chandrasekaran, Chuhan Gao, Brian Tang, Kassem Fawaz, Somesh Jha, Suman Banerjee
2021	—	`conf`	Fourth International Workshop on Dependable and Secure Machine Learning - DSML 2021. DSN Workshops Hui Xu, Guanpeng Li, Homa Alemzadeh, Rakesh Bobba, Varun Chandrasekaran, David E. Evans, Nicolas Papernot, Karthik Pattabiraman, Florian Tramèr
2021	A*	`conf`	Machine Unlearning. SP Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot
2021	J	`jnl`	On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples. CoRR Adelin Travers, Lorna Licollari, Guanghan Wang, Varun Chandrasekaran, Adam Dziedzic, David Lie, Nicolas Papernot
2021	—	`conf`	PowerCut and Obfuscator: An Exploration of the Design Space for Privacy-Preserving Interventions for Smart Speakers. SOUPS @ USENIX Security Symposium Varun Chandrasekaran, Suman Banerjee, Bilge Mutlu, Kassem Fawaz
2021	A*	`conf`	Proof-of-Learning: Definitions and Practice. SP Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot
2021	J	`jnl`	Proof-of-Learning: Definitions and Practice. CoRR Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot
2021	J	`jnl`	SoK: Machine Learning Governance. CoRR Varun Chandrasekaran, Hengrui Jia, Anvith Thudi, Adelin Travers, Mohammad Yaghini, Nicolas Papernot
2021	J	`jnl`	Unrolling SGD: Understanding Factors Influencing Machine Unlearning. CoRR Anvith Thudi, Gabriel Deza, Varun Chandrasekaran, Nicolas Papernot
2020	J	`jnl`	Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers. CoRR Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha, Suman Banerjee
2020	A*	`conf`	Exploring Connections Between Active Learning and Model Extraction. USENIX Security Symposium Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha, Songbai Yan
2020	J	`jnl`	Face-Off: Adversarial Face Obfuscation. CoRR Chuhan Gao, Varun Chandrasekaran, Kassem Fawaz, Somesh Jha
2020	J	`jnl`	On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping. CoRR Sanghyun Hong, Varun Chandrasekaran, Yigitcan Kaya, Tudor Dumitras, Nicolas Papernot
2020	—	`conf`	Third International Workshop on Dependable and Secure Machine Learning - DSML 2020. DSN Workshops Homa Alemzadeh, Rakesh Bobba, Varun Chandrasekaran, David E. Evans, Nicolas Papernot, Karthik Pattabiraman, Florian Tramèr
2019	A*	`conf`	A Framework for Analyzing Spectrum Characteristics in Large Spatio-temporal Scales. MobiCom Yijing Zeng, Varun Chandrasekaran, Suman Banerjee, Domenico Giustiniano
2019	J	`jnl`	Enhancing ML Robustness Using Physical-World Constraints. CoRR Varun Chandrasekaran, Brian Tang, Varsha Pendyala, Kassem Fawaz, Somesh Jha, Xi Wu
2019	J	`jnl`	Generating Semantic Adversarial Examples with Differentiable Rendering. CoRR Lakshya Jain, Wilson Wu, Steven Chen, Uyeong Jang, Varun Chandrasekaran, Sanjit A. Seshia, Somesh Jha
2019	J	`jnl`	Machine Unlearning. CoRR Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, Nicolas Papernot
2018	J	`jnl`	Characterizing Privacy Perceptions of Voice Assistants: A Technology Probe Study. CoRR Varun Chandrasekaran, Kassem Fawaz, Bilge Mutlu, Suman Banerjee
2018	J	`jnl`	Model Extraction and Active Learning. CoRR Varun Chandrasekaran, Kamalika Chaudhuri, Irene Giacomelli, Somesh Jha, Songbai Yan
2018	—	`conf`	Traversing the Quagmire that is Privacy in your Smart Home. IoT S&P@SIGCOMM Chuhan Gao, Varun Chandrasekaran, Kassem Fawaz, Suman Banerjee
2016	—	`conf`	Alphacodes: Usable, Secure Transactions with Untrusted Providers using Human Computable Puzzles. ACM DEV Ashlesh Sharma, Varun Chandrasekaran, Fareeha Amjad, Dennis E. Shasha, Lakshminarayanan Subramanian
2016	J	`jnl`	Secure Mobile Identities. CoRR Varun Chandrasekaran, Fareeha Amjad, Ashlesh Sharma, Lakshminarayanan Subramanian