A Framework for Adversarial Streaming via Differential Privacy and Difference Estimators

Streaming algorithms are algorithms for processing large data streams, using only a limited amount of memory. Classical streaming algorithms operate under the assumption that the input stream is fixed in advance. Recently, there is a growing interest in studying streaming algorithms that provide provable guarantees even when the input stream is chosen by an adaptive adversary. Such streaming algorithms are said to be adversarially-robust. We propose a novel framework for adversarial streaming that hybrids two recently suggested frameworks by Hassidim et al. (2020) and by Woodruff and Zhou (2021). These recently suggested frameworks rely on very different ideas, each with its own strengths and weaknesses. We combine these two frameworks (in a nontrivial way) into a single hybrid framework that gains from both approaches to obtain superior performances for turnstile streams.

[1]  Guy N. Rothblum,et al.  A Multiplicative Weights Mechanism for Privacy-Preserving Data Analysis , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

[2]  Vladimir Braverman,et al.  Adversarial Robustness of Streaming Algorithms through Importance Sampling , 2021, NeurIPS.

[3]  Kobbi Nissim,et al.  Differentially Private Release and Learning of Threshold Functions , 2015, 2015 IEEE 56th Annual Symposium on Foundations of Computer Science.

[4]  Moni Naor,et al.  Sketching in adversarial environments , 2008, STOC.

[5]  David P. Woodruff,et al.  A Framework for Adversarially Robust Streaming Algorithms , 2020, SIGMOD Rec..

[6]  Christopher Jung,et al.  A new analysis of differential privacy’s generalization guarantees (invited paper) , 2019, ITCS.

[7]  David P. Woodruff,et al.  Reusable low-error compressive sampling schemes through privacy , 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).

[8]  Guy N. Rothblum,et al.  Boosting and Differential Privacy , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

[9]  Haim Kaplan,et al.  Privately Learning Thresholds: Closing the Exponential Gap , 2019, COLT.

[10]  Tight Bounds for Adversarially Robust Streams and Sliding Windows via Difference Estimators , 2020, 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS).

[11]  Thomas Steinke,et al.  Composable and versatile privacy via truncated CDP , 2018, STOC.

[12]  Cynthia Dwork,et al.  Calibrating Noise to Sensitivity in Private Data Analysis , 2006, TCC.

[13]  Raef Bassily,et al.  Algorithmic stability for adaptive data analysis , 2015, STOC.

[14]  Amos Beimel,et al.  Private Learning and Sanitization: Pure vs. Approximate Differential Privacy , 2013, APPROX-RANDOM.

[15]  David P. Woodruff,et al.  How robust are linear sketches to adaptive inputs? , 2012, STOC '13.

[16]  Moni Naor,et al.  On the complexity of differentially private data release: efficient algorithms and hardness results , 2009, STOC '09.

[17]  Sudipto Guha,et al.  Graph sketches: sparsification, spanners, and subgraphs , 2012, PODS.

[18]  Thomas Steinke,et al.  Interactive fingerprinting codes and the hardness of preventing false discovery , 2014, 2016 Information Theory and Applications Workshop (ITA).

[19]  Haim Kaplan,et al.  Adversarially Robust Streaming Algorithms via Differential Privacy , 2020, NeurIPS.

[20]  Atri Rudra,et al.  Recovering simple signals , 2012, 2012 Information Theory and Applications Workshop.

[21]  Noga Alon,et al.  The space complexity of approximating the frequency moments , 1996, STOC '96.

[22]  Jonathan Ullman,et al.  Preventing False Discovery in Interactive Data Analysis Is Hard , 2014, 2014 IEEE 55th Annual Symposium on Foundations of Computer Science.

[23]  Kobbi Nissim,et al.  Concentration Bounds for High Sensitivity Functions Through Differential Privacy , 2019, J. Priv. Confidentiality.

[24]  Thomas Steinke,et al.  The Limits of Post-Selection Generalization , 2018, NeurIPS.

[25]  Eylon Yogev,et al.  The Adversarial Robustness of Sampling , 2019, IACR Cryptol. ePrint Arch..

[26]  Haim Kaplan,et al.  Separating Adaptive Streaming from Oblivious Streaming , 2021, ArXiv.

[27]  Sudipto Guha,et al.  Analyzing graph structure via linear measurements , 2012, SODA.

[28]  Toniann Pitassi,et al.  Preserving Statistical Validity in Adaptive Data Analysis , 2014, STOC.