1. Steve Chien, Prateek Jain, Walid Krichene, Yarong Mu, Steffen Rendle, Shuang Song, Abhradeep Thakurta, Li Zhang- Large Scale, Differentially Private Training and Inference with Full Server-Side and Client-Side Data Isolation. Filed US Patent 2022/023438.
2. Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar, and Abhradeep Thakurta- Server Efficient Ehnancement of Privacy in Federated Learning. Filed US Patent 63/035,559.
3. Raef Bassily, Kobbi Nissim, Uri Stemmer, and Abhradeep Thakurta- Systems And Methods For Improving Data Privacy Using Distributed Private Histograms. Granted US Patent: 11023594.
4. Yannick L. Sierra, Abhradeep Thakurta, Umesh S. Vaishampayan, John C. Hurley, Keaton F. Mowery, and Michael Brouwer- Efficient implementation for differential privacy using cryptographic functions (*). Granted US Patent: 10552631.
5. Abhradeep Thakurta, Andrew H. Vyrros, Umesh S. Vaishampayan, Gaurav Kapoor, Julien Freudinger, Vipul Ved Prakash, Arnaud Legendre, and Steven Duplinsky- Emoji frequency detection and deep link frequency (*). Granted US Patents: 9712550 and 9705908.
6. Abhradeep Thakurta, Andrew H. Vyrros, Umesh S. Vaishampayan, Gaurav Kapoor, Julien Freudiger, Vivek Rangarajan Sridhar, and Doug Davidson- Learning New Words (*). Granted US Patents: 9594741 and 9645998.

1. Raef Bassily (PI), and Abhradeep Tkhakurta (PI). Google faculty award (2019). 50K USD.
2. Abhradeep Thakurta (PI), Russell Corbett-Detig, Dimitris Achlioptas, and Vishesh Karwa. TRIPODS+X:RES: Collaborative Research:Privacy-Preserving Genomic Data Analysis (2018-2021). 600K USD.
3. Raef Bassily (PI), Abhradeep Thakurta, and Bo Li. AF: Small: Collaborative Research: Rigorous Approaches for Scalable Privacy-preserving Deep Learning (2018-2021). 500K USD.
4. Lise Getoor (PI), C. Seshadhri, Abel Rodriguez, Dimitris Achlioptas, Abhradeep Thakurta, Rajarshi Guhaniyogi, and Daniel Venturi. NSF TRIPODS: Towards a Unified Theory of Structure, Incompleteness & Uncertainty in Heterogeneous Graphs (2017-2020). 1.5 million USD.

Journals and Surveys

1. 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 Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, and Wanrong Zhang. Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment. Harvard Data Science Review, 2024.
2. Georgina Evans, Gary King, Adam Smith, and Abhradeep Thakurta. Differentially Private Survey Research. American Journal of Political Science, 2022.
3. Georgina Evans, Gary King, Margaret Schwenzfeier, and Abhradeep Thakurta. Statistically Valid Inferences from Privacy Protected Data. American Political Science Review, 2022.
4. Raef Bassily, Kobbi Nissim , Abhradeep Thakurta, and Uri Stemmer. Practical Locally Private Heavy Hitters. Journal of Machine Learning Research, 2020.
5. Daniel Kifer, Solomon Messing, Aaron Roth, Abhradeep Thakurta, and Danfeng Zhang. Guidelines for Implementing and Auditing Differentially Private Systems, 2020.
6. Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, and Nithin Varma. Erasure-Resilient Property Testing. In SIAM Journal of Computing 2018.
7. Abhradeep Thakurta. Beyond Worst Case Sensitivity in Private Data Analysis. [Survey article. Encylopedia of Algorithms, 2015].

Conferences and Workshops

2024


1. Krishnamurthy Dvijotham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, and Abhradeep Thakurta- Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy. In FOCS 2024.
2. Naman Agarwal, Satyen Kale, Karan Singh, and Abhradeep Thakurta- Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements. In ICML 2024.
3. Gavin Brown, Krishnamurthy Dj Dvijotham, Georgina Evans, Daogao Liu, Adam Smith, and Abhradeep Thakurta- Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation. In ICML 2024.
4. Bing Zhang, Vadym Doroshenko, Peter Kairouz, Thomas Steinke, Abhradeep Thakurta, Ziyin Ma, Eidan Cohen, Himani Apte, and Jodi Spacek- Differentially Private Stream Processing at Scale (*). In VLDB [Industry track] 2024. (Authors two to five contributed equally.)
5. Christopher A. Choquette-Choo, Arun Ganesh, Thomas Steinke, and Abhradeep Thakurta- Privacy Amplification for Matrix Mechanisms. In ICLR 2024 [Spotlight].
6. Christopher A. Choquette-Choo, Krishnamurthy Dj Dvijotham, Krishna Pillutla, Arun Ganesh, Thomas Steinke, and Abhradeep Thakurta- Correlated Noise Provably Beats Independent Noise for Differentially Private Learning (*). In ICLR 2024.
7. Soumyabrata Pal, Prateek Varshney, Prateek Jain, Abhradeep Thakurta, Gagan Madan, Gaurav Aggarwal, Pradeep Shenoy, and Gaurav Srivastava- Sample-Efficient Personalization: Modeling User Parameters as Low Rank Plus Sparse Components (*). In AISTATS 2024.
8. Walid Krichene, Nicolas Mayoraz, Steffen Rendle, Shuang Song, Abhradeep Thakurta, and Li Zhang- Private Learning with Public Features. In AISTATS 2024.

2023


9. Arun Ganesh, Mahdi Haghifam, Thomas Steinke, and Abhradeep Thakurta- Faster Differentially Private Convex Optimization via Second-Order Methods. In NeurIPS 2023.
10. Stephan Rabanser, Anvith Thudi, Abhradeep Thakurta, Krishnamurthy Dj Dvijotham, and Nicolas Papernot- Training Private Models That Know What They Don’t Know (*). In NeurIPS 2023.
11. Arun Ganesh, Daogao Liu, Sewoong Oh, and Abhradeep Thakurta- Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks. In NeurIPS 2023 [Spotlight].
12. Christopher A. Choquette-Choo, Arun Ganesh, Ryan McKenna, Hugh Brendan McMahan, Keith Rush, Abhradeep Thakurta, and Zheng Xu- (Amplified) Banded Matrix Factorization: A unified approach to private training. In NeurIPS 2023.
13. Arun Ganesh, Abhradeep Thakurta, and Jalaj Upadhyay- Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets. In COLT 2023.
14. Naman Agarwal, Satyen Kale, Karan Singh, and Abhradeep Thakurta- Differentially Private and Lazy Online Convex Optimization. In COLT 2023.
15. Prateek Jain, Walid Krichene, Shuang Song, Abhradeep Thakurta, and Li Zhang- Multi-task Differential Privacy under Distribution Skew. In ICML 2023.
16. Arun Ganesh, Mahdi Haghifam, Milad Nasr, Seewong Oh, Thomas Steinke, Om Thakkar, Abhradeep Thakurta, and Lun Wang- Why is Public Data Necessary for Private Model Training. In ICML 2023.
17. Christopher A. Choquette-Choo, Brendan McMahan, Keith Rush, and Abhradeep Thakurta.- Multi-Epoch Matrix Factorization Mechnisms for Private Machine Learning. In ICML 2023 [Oral].
18. Matthew Jagielski, Om Thakkar, Florian Tramèr, Daphne Ippolito, Katherine Lee, Nicholas Carlini, Eric Wallace, Shuang Song, Abhradeep Thakurta, Nicolas Papernot, and Chiyuan Zhang- Measuring Forgetting of Memorized Training Examples (*). ICLR 2023.
19. Harsh Mehta, Abhradeep Thakurta, Alexey Kurakin, and Ashok Cutkosky- Large Scale Transfer Learning for Differentially Private Image Classification(*). [Accepted, TMLR 2023].
20. Harsh Mehta, Walid Krichene, Abhradeep Thakurta, Alexey Kurakin, and Ashok Cutkosky- Differentially Private Image Classification from Features (*). [Accepted, TMLR 2023].

2022


21. Xuechen Li, Daogao Liu, Tatsunori Hashimoto, Huseyin A. Inan, Janardhan Kulkarni, Yin Tat Lee, and Abhradeep Thakurta- When Does Differentially Private Learning Not Suffer in High Dimensions?. In NeurIPS 2022.
22. Sergey Denisov, Brendan McMahan, Keith Rush, Adam Smith, and Abhradeep Thakurta- Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams . In NeurIPS 2022.
23. Prateek Jain, Abhradeep Thakurta, and Prateek Varshney- (Nearly) Optimal Private Linear Regression for Sub-Gaussian Data via Adaptive Clipping. In COLT 2022.
24. Satyen Kale, Oren Mangoubi, Abhradeep Thakurta, Nisheeth Vishnoi, and Yikai Wu- Private Matrix Approximation and Geometry of Unitary Orbits. In COLT 2022.
25. Eshan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith Suriyakumar, Om Thakkar, and Abhradeep Thakurta- Public Data-Assisted Mirror Descent for Private Model Training. In ICML 2022.
26. Ameya Daigavane, Gagan Madan, Aditya Sinha, Abhradeep Guha Thakurta, Gaurav Aggarwal, Prateek Jain- Node-Level Privacy Preserving Graph Neural Networks. In Pair2Struct workshop (ICLR 2022).

2021


27. Prateek Jain, Keith Rush, Adam Smith, Shuang Song, and Abhradeep Thakurta- Differentially Private Model Personalization. In NeurIPS 2021 (Spotlight) and TPDP (Workshop) 2021.
28. Sanjam Garg, Somesh Jha, Mohammad Mahmoody, Saeed Mahloujifar, and Abhradeep Thakurta- A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks. In NeurIPS 2021, and Uncertainty & Robustness in Deep Learning (UDL) (Workshop) 2020.
29. Peter Kairouz, Monica Ribero, Keith Rush, and Abhradeep Thakurta- Fast Dimension Independent Private AdaGrad on Publicly Estimated Subspaces. In COLT 2021.
30. Steve Chein, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Thakurta, and Li Zhang- Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates. In ICML 2021 [Long Oral (Acceptance rate: 3%)].
31. Peter Kairouz, Brendan McMahan, Shuang Song, On Thakkar, Abhradeep Thakurta, and Zheng Xu- Practical and Private (Deep) Learning without Sampling or Shuffling. In ICML 2021.
32. Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Abhradeep Thakurta, and Florian Tramer- Is Private Learning Possible with Instance Encoding?. In IEEE S and P (Oakland) 2021.
33. Milad Nasr, Nicholas Carlini, Nicolas Papernot, Shuang Song, and Abhradeep Thakurta- Adversary Instantiation: Lower bounds for differentially private machine learning (*). In IEEE S and P (Oakland) 2021.
34. Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien, and Úlfar Erlingsson- Tempered Sigmoid Activations for Deep Learning with Differential Privacy (*). In AAAI 2021 and TPDP (Workshop) 2020.
35. Shuang Song, Thomas Steinke, Om Thakkar, and Abhradeep Thakurta- Evading the Curse of Dimensionality in Unconstrained Private GLMs. In AISTATS 2021, TPDP (Workshop, Oral) 2020 and PPML (Workshop) 2020.

2020


36. Georgina Evans, Gary King, Margaret Schwenzfeier, and Abhradeep Thakurta-Statistically Valid Inferences from Privacy Protected Data. [Working paper]
37. Georgina Evans, Gary King, Adam Smith, and Abhradeep Thakurta- Differentially Private Survey Research. [Working paper]
38. Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Shuang Song, Kunal Talwar, and Abhradeep Thakurta- Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation. In Theory and Practices of Differential Privacy (TPDP) (Workshop) 2020.
39. Borja Balle, Peter Kairouz, H. Brendan McMahan, Om Thakkar, and Abhradeep Thakurta- Privacy Amplification by Random Check-Ins. In NeurIPS 2020 and TPDP (Workshop) 2020.
40. Adam Smith, Shuang Song, and Abhradeep Thakurta- The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space. In NeurIPS 2020.

2019


41. Raef Bassily, Vitaly Feldman, Kunal Talwar, and Abhradeep Thakurta- Private Stochastic Convex Optimization. In NeurIPS 2019 [Spotlight].
42. Ulfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Kunal Talwar, and Abhradeep Thakurta- Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. In SODA 2019.
43. Joe Near, Dawn Song, Om Thakkar, Abhradeep Thakurta, and Lun Wang- Towards Practical Differentially Private Convex Optimization. In IEEE S and P 2019.

2018


44. Raef Bassily, Om Thakkar , and Abhradeep Thakurta- Model Agnostic Private Learning via Stability. In NeurIPS 2018 [Long Oral (Acceptance: 0.6%)]
45. Vitaly Feldman, Ilya Mironov, Kunal Talwar, and Abhradeep Thakurta- Privacy Amplification by Iteration. In FOCS 2018.
46. Prateek Jain, Om Thakkar , and Abhradeep Thakurta- Differentially Private Matrix Completion, Revisited. In ICML 2018 [Long Oral]

2017


47. Raef Bassily, Kobbi Nissim , Abhradeep Thakurta, and Uri Stemmer- Practical Locally Private Heavy Hitters. In NeurIPS 2017, and Journal of Machine Learning Research 2020.
48. Adam Smith, Abhradeep Thakurta, and Jalaj Upadhay- Is Interaction Necessary for Distributed Private Learning? In IEEE S and P (Oakland), 2017.

2016


49. Kashyap Dixit, Sofya Raskhodnikova, Abhradeep Thakurta, and Nithin Varma- Erasure-Resilient Property Testing. In ICALP 2016, and SIAM Journal of Computing 2018.

2015


50. Kunal Talwar, Abhradeep Thakurta, and Li Zhang- Nearly optimal private LASSO. In NeurIPS 2015.
51. Nikita Mishra and Abhradeep Thakurta- (Nearly) Optimal Differentially Private Stochastic Multi-arm Bandits: From Theory to Practice. In UAI 2015.
52. Ruggerio Cavallo, Abhradeep Thakurta, and Chris Wilkins- Truthful Dynamic Mechanisms for Multi-Armed Bandits. In AdAuctions Workshop, EC 2015.

2014


53. Raef Bassily, Adam Smith, and Abhradeep Thakurta- Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds. In FOCS 2014.
54. Cynthia Dwork, Kunal Talwar, Abhradeep Thakurta, and Li Zhang- Analyze Gauss: Optimal Bounds for Privacy-Preserving Principal Component Analysis. In STOC 2014.
55. Prateek Jain, and Abhradeep Thakurta- (Near) Dimension Independent Risk Bounds for Differentially Private Learning. In ICML 2014.

2013


56. Adam Smith and Abhradeep Thakurta- (Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings. In NeurIPS 2013.
57. Adam Smith and Abhradeep Thakurta- Differentially Private Feature Selection via Stability Arguments, and the Robustness of LASSO. In COLT 2013.
58. Prateek Jain and Abhradeep Thakurta- Differentially Private Learning with Kernels. In ICML 2013.
59. Kashyap Dixit, Madhav Jha, Sofya Raskhodnikova, and Abhradeep Thakurta- Testing Lipschitz Property over Product Distributions with Applications to Statistical Data Privacy. In TCC 2013.

2012


60. Prateek Jain and Abhradeep Thakurta- Mirror Descent based Interactive Database Privacy. In APPROX/ RANDOM 2012.
61. Daniel Kifer, Adam Smith, and Abhradeep Thakurta- Private Convex Empirical Risk Minimization and High-dimensional Regression. In COLT 2012.
62. Prateek Jain, Pravesh Kothari, and Abhradeep Thakurta- Differentially Private Online Learning. In COLT 2012.
63. Prashanth Mohan, Abhradeep Thakurta, Elaine Shi, and Dawn Song- GUPT: Privacy Preserving Data Analysis Made Easy (*). In SIGMOD 2012.

2011


64. Raghav Bhaskar, Abhishek Bhowmick, Vipul Goyal, Srivatsan Laxman, and Abhradeep Thakurta-Noiseless Database Privacy. In Asiacrypt, 2011.

2010


65. Raghav Bhaskar, Srivatsan Laxman, Adam Smith, and Abhradeep Thakurta- Discovering frequent patterns in sensitive data. In SIGKDD, 2010.
66. Prateek Jain, Vivek Kulkarni, Abhradeep Thakurta, and Oliver Williams.- To Drop or Not to Drop: Generalizability, Stability and Privacy of Dropout. [Manuscript.]