Abhradeep Thakurta

102 papers A* 26A 5B 1Journal 63Unranked 6

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Reinforced Generation of Combinatorial Structures: Ramsey Numbers. CoRR Ansh Nagda, Prabhakar Raghavan, Abhradeep Thakurta
2025	J	`jnl`	Correlated Noise Mechanisms for Differentially Private Learning. CoRR Krishna Pillutla, Jalaj Upadhyay, Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Arun Ganesh, Monika Henzinger, Jonathan Katz, Ryan McKenna, H. Brendan McMahan, Keith Rush, Thomas Steinke, Abhradeep Thakurta
2025	J	`jnl`	Hush! Protecting Secrets During Model Training: An Indistinguishability Approach. CoRR Arun Ganesh, Brendan McMahan, Milad Nasr, Thomas Steinke, Abhradeep Thakurta
2025	J	`jnl`	On Design Principles for Private Adaptive Optimizers. CoRR Arun Ganesh, Brendan McMahan, Abhradeep Thakurta
2025	J	`jnl`	Recycling Scraps: Improving Private Learning by Leveraging Checkpoints]{Recycling Scraps: Improving Private Learning by Leveraging Checkpoints. Proc. Priv. Enhancing Technol. Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Yarong Mu, Shuang Song, Om Thakkar, Abhradeep Thakurta, Xinyi Zheng
2025	J	`jnl`	Reinforced Generation of Combinatorial Structures: Applications to Complexity Theory. CoRR Ansh Nagda, Prabhakar Raghavan, Abhradeep Thakurta
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	J	`jnl`	Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models. CoRR Hongbin Liu, Lun Wang, Om Thakkar, Abhradeep Thakurta, Arun Narayanan
2024	J	`jnl`	Differentially Private Stream Processing at Scale. Proc. VLDB Endow. Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Eidan Cohen, Himani Apte, Jodi Spacek
2024	A*	`conf`	Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy. FOCS Krishnamurthy Dj Dvijotham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, Abhradeep Thakurta
2024	J	`jnl`	Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy. CoRR Krishnamurthy Dvijotham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, Abhradeep Thakurta
2024	J	`jnl`	Near Exact Privacy Amplification for Matrix Mechanisms. CoRR Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Thakurta
2024	J	`jnl`	Optimal Rates for DP-SCO with a Single Epoch and Large Batches. CoRR Christopher A. Choquette-Choo, Arun Ganesh, Abhradeep Thakurta
2024	J	`jnl`	Preserving Expert-Level Privacy in Offline Reinforcement Learning. CoRR Navodita Sharma, Vishnu Vinod, Abhradeep Thakurta, Alekh Agarwal, Borja Balle, Christoph Dann, Aravindan Raghuveer
2024	J	`jnl`	Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation. CoRR Gavin Brown, Krishnamurthy Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, Abhradeep Thakurta
2024	A	`conf`	Private Learning with Public Features. AISTATS Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
2024	A	`conf`	Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components. AISTATS Soumyabrata Pal, Prateek Varshney, Gagan Madan, Prateek Jain, Abhradeep Thakurta, Gaurav Aggarwal, Pradeep Shenoy, Gaurav Srivastava
2024	—	`conf`	Training Large ASR Encoders With Differential Privacy. SLT Geeticka Chauhan, Steve Chien, Om Thakkar, Abhradeep Thakurta, Arun Narayanan
2024	J	`jnl`	Training Large ASR Encoders with Differential Privacy. CoRR Geeticka Chauhan, Steve Chien, Om Thakkar, Abhradeep Thakurta, Arun Narayanan
2023	J	`jnl`	Challenges towards the Next Frontier in Privacy. CoRR Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie J. Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
2023	J	`jnl`	Correlated Noise Provably Beats Independent Noise for Differentially Private Learning. CoRR Christopher A. Choquette-Choo, Krishnamurthy Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
2023	J	`jnl`	Differentially Private Stream Processing at Scale. CoRR Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Himani Apte, Jodi Spacek
2023	A*	`conf`	Differentially Private and Lazy Online Convex Optimization. COLT Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Thakurta
2023	J	`jnl`	Faster Differentially Private Convex Optimization via Second-Order Methods. CoRR Arun Ganesh, Mahdi Haghifam, Thomas Steinke, Abhradeep Thakurta
2023	J	`jnl`	How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy. CoRR Natalia Ponomareva, Hussein Hazimeh, Alex Kurakin, Zheng Xu, Carson Denison, H. Brendan McMahan, Sergei Vassilvitskii, Steve Chien, Abhradeep Thakurta
2023	J	`jnl`	Multi-Task Differential Privacy Under Distribution Skew. CoRR Walid Krichene, Prateek Jain, Shuang Song, Mukund Sundararajan, Abhradeep Thakurta, Li Zhang
2023	J	`jnl`	Privacy Amplification for Matrix Mechanisms. CoRR Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, Abhradeep Thakurta
2023	J	`jnl`	Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. CoRR Arun Ganesh, Daogao Liu, Sewoong Oh, Abhradeep Thakurta
2023	J	`jnl`	Private Learning with Public Features. CoRR Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
2023	J	`jnl`	Training Private Models That Know What They Don't Know. CoRR Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dvijotham, Nicolas Papernot
2023	A*	`conf`	Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets. COLT Arun Ganesh, Abhradeep Thakurta, Jalaj Upadhyay
2023	J	`jnl`	Why Is Public Pretraining Necessary for Private Model Training? CoRR Arun Ganesh, Mahdi Haghifam, Milad Nasr, Sewoong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, Lun Wang
2022	A*	`conf`	(Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping. COLT Prateek Varshney, Abhradeep Thakurta, Prateek Jain
2022	J	`jnl`	(Nearly) Optimal Private Linear Regression via Adaptive Clipping. CoRR Prateek Varshney, Abhradeep Thakurta, Prateek Jain
2022	J	`jnl`	Differentially Private Image Classification from Features. CoRR Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky
2022	J	`jnl`	Fine-Tuning with Differential Privacy Necessitates an Additional Hyperparameter Search. CoRR Yannis Cattan, Christopher A. Choquette-Choo, Nicolas Papernot, Abhradeep Thakurta
2022	J	`jnl`	Fully Adaptive Composition for Gaussian Differential Privacy. CoRR Adam D. Smith, Abhradeep Thakurta
2022	J	`jnl`	Langevin Diffusion: An Almost Universal Algorithm for Private Euclidean (Convex) Optimization. CoRR Arun Ganesh, Abhradeep Thakurta, Jalaj Upadhyay
2022	J	`jnl`	Large Scale Transfer Learning for Differentially Private Image Classification. CoRR Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin, Ashok Cutkosky
2022	J	`jnl`	Measuring Forgetting of Memorized Training Examples. CoRR Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Chiyuan Zhang
2022	J	`jnl`	Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning. CoRR Christopher A. Choquette-Choo, H. Brendan McMahan, Keith Rush, Abhradeep Thakurta
2022	A*	`conf`	Private Matrix Approximation and Geometry of Unitary Orbits. COLT Oren Mangoubi, Yikai Wu, Satyen Kale, Abhradeep Thakurta, Nisheeth K. Vishnoi
2022	A*	`conf`	Public Data-Assisted Mirror Descent for Private Model Training. ICML Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
2022	J	`jnl`	Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints. CoRR Virat Shejwalkar, Arun Ganesh, Rajiv Mathews, Om Thakkar, Abhradeep Thakurta
2022	J	`jnl`	Toward Training at ImageNet Scale with Differential Privacy. CoRR Alexey Kurakin, Steve Chien, Shuang Song, Roxana Geambasu, Andreas Terzis, Abhradeep Thakurta
2021	A*	`conf`	(Nearly) Dimension Independent Private ERM with AdaGrad Ratesvia Publicly Estimated Subspaces. COLT Peter Kairouz, Mónica Ribero Diaz, Keith Rush, Abhradeep Thakurta
2021	A*	`conf`	Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. SP Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
2021	J	`jnl`	Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning. CoRR Milad Nasr, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, Nicholas Carlini
2021	A	`conf`	Evading the Curse of Dimensionality in Unconstrained Private GLMs. AISTATS Shuang Song, Thomas Steinke, Om Thakkar, Abhradeep Thakurta
2021	A*	`conf`	Is Private Learning Possible with Instance Encoding? SP Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta, Florian Tramèr
2021	A*	`conf`	Practical and Private (Deep) Learning Without Sampling or Shuffling. ICML Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu
2021	J	`jnl`	Practical and Private (Deep) Learning without Sampling or Shuffling. CoRR Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta, Zheng Xu
2021	A*	`conf`	Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. ICML Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
2021	J	`jnl`	Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. CoRR Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang
2021	J	`jnl`	Public Data-Assisted Mirror Descent for Private Model Training. CoRR Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith M. Suriyakumar, Om Thakkar, Abhradeep Thakurta
2021	A*	`conf`	Tempered Sigmoid Activations for Deep Learning with Differential Privacy. AAAI Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson
2020	J	`jnl`	An Attack on InstaHide: Is Private Learning Possible with Instance Encoding? CoRR Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, Florian Tramèr
2020	J	`jnl`	Characterizing Private Clipped Gradient Descent on Convex Generalized Linear Problems. CoRR Shuang Song, Om Thakkar, Abhradeep Thakurta
2020	J	`jnl`	Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning. CoRR Peter Kairouz, Mónica Ribero, Keith Rush, Abhradeep Thakurta
2020	J	`jnl`	Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation. CoRR Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Shuang Song, Kunal Talwar, Abhradeep Thakurta
2020	J	`jnl`	Guidelines for Implementing and Auditing Differentially Private Systems. CoRR Daniel Kifer, Solomon Messing, Aaron Roth, Abhradeep Thakurta, Danfeng Zhang
2020	J	`jnl`	Obliviousness Makes Poisoning Adversaries Weaker. CoRR Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta
2020	J	`jnl`	Practical Locally Private Heavy Hitters. J. Mach. Learn. Res. Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Thakurta
2020	A*	`conf`	Privacy Amplification via Random Check-Ins. NeurIPS Borja Balle, Peter Kairouz, Brendan McMahan, Om Dipakbhai Thakkar, Abhradeep Thakurta
2020	J	`jnl`	Privacy Amplification via Random Check-Ins. CoRR Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar, Abhradeep Thakurta
2020	J	`jnl`	Tempered Sigmoid Activations for Deep Learning with Differential Privacy. CoRR Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, Úlfar Erlingsson
2020	A*	`conf`	The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space. NeurIPS Adam D. Smith, Shuang Song, Abhradeep Thakurta
2019	A*	`conf`	Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. SODA Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta
2019	—	`conf`	Privacy-preserving Data Mining in Industry. WWW (Companion Volume) Krishnaram Kenthapadi, Ilya Mironov, Abhradeep Thakurta
2019	J	`jnl`	Private Stochastic Convex Optimization with Optimal Rates. CoRR Raef Bassily, Vitaly Feldman, Kunal Talwar, Abhradeep Thakurta
2019	A*	`conf`	Towards Practical Differentially Private Convex Optimization. IEEE Symposium on Security and Privacy Roger Iyengar, Joseph P. Near, Dawn Song, Om Thakkar, Abhradeep Thakurta, Lun Wang
2018	J	`jnl`	Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. CoRR Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, Abhradeep Thakurta
2018	A*	`conf`	Differentially Private Matrix Completion Revisited. ICML Prateek Jain, Om Dipakbhai Thakkar, Abhradeep Thakurta
2018	J	`jnl`	Erasure-Resilient Property Testing. SIAM J. Comput. Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, Nithin Varma
2018	J	`jnl`	Model-Agnostic Private Learning via Stability. CoRR Raef Bassily, Om Thakkar, Abhradeep Thakurta
2018	A*	`conf`	Privacy Amplification by Iteration. FOCS Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta
2018	J	`jnl`	Privacy Amplification by Iteration. CoRR Vitaly Feldman, Ilya Mironov, Kunal Talwar, Abhradeep Thakurta
2017	J	`jnl`	Differentially Private Matrix Completion, Revisited. CoRR Prateek Jain, Om Thakkar, Abhradeep Thakurta
2017	A*	`conf`	Is Interaction Necessary for Distributed Private Learning? IEEE Symposium on Security and Privacy Adam D. Smith, Abhradeep Thakurta, Jalaj Upadhyay
2017	J	`jnl`	Practical Locally Private Heavy Hitters. CoRR Raef Bassily, Kobbi Nissim, Uri Stemmer, Abhradeep Thakurta
2016	—	`ch.`	Beyond Worst Case Sensitivity in Private Data Analysis. Encyclopedia of Algorithms Abhradeep Thakurta
2016	A*	`conf`	Erasure-Resilient Property Testing. ICALP Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, Nithin Varma
2016	J	`jnl`	Erasure-Resilient Property Testing. CoRR Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, Nithin Varma
2015	A	`conf`	(Nearly) Optimal Differentially Private Stochastic Multi-Arm Bandits. UAI Nikita Mishra, Abhradeep Thakurta
2015	—	`conf`	Nearly Optimal Private LASSO. NIPS Kunal Talwar, Abhradeep Thakurta, Li Zhang
2015	J	`jnl`	To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout. CoRR Prateek Jain, Vivek Kulkarni, Abhradeep Thakurta, Oliver Williams
2014	A*	`conf`	Analyze gauss: optimal bounds for privacy-preserving principal component analysis. STOC Cynthia Dwork, Kunal Talwar, Abhradeep Thakurta, Li Zhang
2014	J	`jnl`	Private Empirical Risk Minimization Beyond the Worst Case: The Effect of the Constraint Set Geometry. CoRR Kunal Talwar, Abhradeep Thakurta, Li Zhang
2014	J	`jnl`	Private Empirical Risk Minimization, Revisited. CoRR Raef Bassily, Adam D. Smith, Abhradeep Thakurta
2014	A*	`conf`	Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds. FOCS Raef Bassily, Adam D. Smith, Abhradeep Thakurta
2013	A*	`conf`	Differentially Private Feature Selection via Stability Arguments, and the Robustness of the Lasso. COLT Abhradeep Thakurta, Adam D. Smith
2013	—	`conf`	Differentially Private Learning with Kernels. ICML (3) Prateek Jain, Abhradeep Thakurta
2013	B	`conf`	Testing the Lipschitz Property over Product Distributions with Applications to Data Privacy. TCC Kashyap Dixit, Madhav Jha, Sofya Raskhodnikova, Abhradeep Thakurta
2012	A*	`conf`	Differentially Private Online Learning. COLT Prateek Jain, Pravesh Kothari, Abhradeep Thakurta
2012	—	`conf`	GUPT: privacy preserving data analysis made easy. SIGMOD Conference Prashanth Mohan, Abhradeep Thakurta, Elaine Shi, Dawn Song, David E. Culler
2012	—	`conf`	Mirror Descent Based Database Privacy. APPROX-RANDOM Prateek Jain, Abhradeep Thakurta
2012	A*	`conf`	Private Convex Optimization for Empirical Risk Minimization with Applications to High-dimensional Regression. COLT Daniel Kifer, Adam D. Smith, Abhradeep Thakurta
2012	J	`jnl`	Testing Lipschitz Property over Product Distribution and its Applications to Statistical Data Privacy CoRR Kashyap Dixit, Madhav Jha, Abhradeep Thakurta
2011	J	`jnl`	Differentially Private Online Learning CoRR Prateek Jain, Pravesh Kothari, Abhradeep Thakurta
2011	A	`conf`	Noiseless Database Privacy. ASIACRYPT Raghav Bhaskar, Abhishek Bhowmick, Vipul Goyal, Srivatsan Laxman, Abhradeep Thakurta
2011	J	`jnl`	Noiseless Database Privacy. IACR Cryptol. ePrint Arch. Raghav Bhaskar, Abhishek Bhowmick, Vipul Goyal, Srivatsan Laxman, Abhradeep Thakurta
2010	A*	`conf`	Discovering frequent patterns in sensitive data. KDD Raghav Bhaskar, Srivatsan Laxman, Adam D. Smith, Abhradeep Thakurta