Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Improved Algorithms for White-Box Adversarial Streams (2307.03529v1)

Published 7 Jul 2023 in cs.DS

Abstract: We study streaming algorithms in the white-box adversarial stream model, where the internal state of the streaming algorithm is revealed to an adversary who adaptively generates the stream updates, but the algorithm obtains fresh randomness unknown to the adversary at each time step. We incorporate cryptographic assumptions to construct robust algorithms against such adversaries. We propose efficient algorithms for sparse recovery of vectors, low rank recovery of matrices and tensors, as well as low rank plus sparse recovery of matrices, i.e., robust PCA. Unlike deterministic algorithms, our algorithms can report when the input is not sparse or low rank even in the presence of such an adversary. We use these recovery algorithms to improve upon and solve new problems in numerical linear algebra and combinatorial optimization on white-box adversarial streams. For example, we give the first efficient algorithm for outputting a matching in a graph with insertions and deletions to its edges provided the matching size is small, and otherwise we declare the matching size is large. We also improve the approximation versus memory tradeoff of previous work for estimating the number of non-zero elements in a vector and computing the matrix rank.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. Adversarial laws of large numbers and optimal regret in online classification. In STOC ’21: 53rd Annual ACM SIGACT Symposium on Theory of Computing, pages 447–455, 2021.
  2. The white-box adversarial data stream model. In Proceedings of the 41st ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, PODS ’22, page 15–27, New York, NY, USA, 2022. Association for Computing Machinery.
  3. A framework for adversarial streaming via differential privacy and difference estimators. CoRR, abs/2107.14527, 2021.
  4. Solving the shortest vector problem in 2n time using discrete gaussian sampling: Extended abstract. In Proceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing, STOC ’15, page 733–742, New York, NY, USA, 2015. Association for Computing Machinery.
  5. The space complexity of approximating the frequency moments. In Proceedings of the Twenty-Eighth Annual ACM Symposium on Theory of Computing, STOC ’96, page 20–29, New York, NY, USA, 1996. Association for Computing Machinery.
  6. The space complexity of approximating the frequency moments. J. Comput. Syst. Sci., 58(1):137–147, 1999.
  7. Evasion attacks against machine learning at test time. In Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD, Proceedings, Part III, pages 387–402, 2013.
  8. A framework for adversarially robust streaming algorithms. In Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, PODS’20, page 63–80, New York, NY, USA, 2020. Association for Computing Machinery.
  9. Adversarially robust streaming via dense-sparse trade-offs. In 5th Symposium on Simplicity in Algorithms, SOSA, 2022.
  10. Toward automated large-scale information integration and discovery. In Data Management in a Connected World, Essays Dedicated to Hartmut Wedekind on the Occasion of His 70th Birthday, pages 161–180, 2005.
  11. Adversarial robustness of streaming algorithms through importance sampling. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems, NeurIPS, 2021.
  12. A framework for adversarially robust streaming algorithms. SIGMOD Rec., 50(1):6–13, 2021.
  13. Pseudorandom functions and lattices. volume 2011, page 401, 01 2011.
  14. Random oracles are practical: A paradigm for designing efficient protocols. In Proceedings of the 1st ACM Conference on Computer and Communications Security, CCS ’93, page 62–73, New York, NY, USA, 1993. Association for Computing Machinery.
  15. The exact security of digital signatures-how to sign with rsa and rabin. In Ueli Maurer, editor, Advances in Cryptology — EUROCRYPT ’96, pages 399–416, Berlin, Heidelberg, 1996. Springer Berlin Heidelberg.
  16. The adversarial robustness of sampling. In Proceedings of the 39th ACM SIGMOD-SIGACT-SIGAI Symposium on Principles of Database Systems, PODS, pages 49–62, 2020.
  17. A simple sketching algorithm for entropy estimation over streaming data. In International Conference on Artificial Intelligence and Statistics, 2013.
  18. The random oracle methodology, revisited. J. ACM, 51(4):557–594, jul 2004.
  19. Adversarially robust coloring for graph streams. In 13th Innovations in Theoretical Computer Science Conference, ITCS, 2022.
  20. More dynamic data structures for geometric set cover with sublinear update time. In 37th International Symposium on Computational Geometry, SoCG, pages 25:1–25:14, 2021.
  21. Timothy M. Chan. A dynamic data structure for 3-d convex hulls and 2-d nearest neighbor queries. J. ACM, 57(3):16:1–16:15, 2010.
  22. Fast matrix rank algorithms and applications. J. ACM, 60(5):31:1–31:25, 2013.
  23. Robust principal component analysis? J. ACM, 58(3), jun 2011.
  24. Rank-sparsity incoherence for matrix decomposition. SIAM Journal on Optimization, 21(2):572–596, 2011.
  25. An introduction to compressive sampling. IEEE Signal Process. Mag., 25(2):21–30, 2008.
  26. Autoaugment: Learning augmentation policies from data. CoRR, abs/1805.09501, 2018.
  27. Mining database structure; or, how to build a data quality browser. In Proceedings of the 2002 ACM SIGMOD International Conference on Management of Data, pages 240–251, 2002.
  28. Making data structures persistent. J. Comput. Syst. Sci., 38(1):86–124, 1989.
  29. Making data structures confluently persistent. J. Algorithms, 48(1):16–58, 2003.
  30. How to construct random functions. J. ACM, 33(4):792–807, aug 1986.
  31. Iterative hard thresholding for low cp-rank tensor models. 08 2019.
  32. Deterministic k-set structure. In Stijn Vansummeren, editor, Proceedings of the Twenty-Fifth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, June 26-28, 2006, Chicago, Illinois, USA, pages 280–289. ACM, 2006.
  33. Explaining and harnessing adversarial examples. CoRR, abs/1412.6572, 2014.
  34. Adversarially robust streaming algorithms via differential privacy. In Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, NeurIPS, 2020.
  35. Adversarial attacks on neural network policies. In 5th International Conference on Learning Representations, ICLR, 2017.
  36. Prior convictions: Black-box adversarial attacks with bandits and priors. CoRR, abs/1807.07978, 2018.
  37. Sina Jafarpour. Deterministic Compressed Sensing. PhD thesis, Princeton University, 2011.
  38. Towards optimal moment estimation in streaming and distributed models. ACM Trans. Algorithms, may 2023. Just Accepted.
  39. Haim Kaplan. Persistent data structures. In Handbook of Data Structures and Applications. Chapman and Hall/CRC, 2004.
  40. Charles F. F. Karney. Sampling exactly from the normal distribution. ACM Trans. Math. Softw., 42(1), jan 2016.
  41. Adversarial machine learning at scale. In 5th International Conference on Learning Representations, ICLR, Conference Track Proceedings, 2017.
  42. Sam B. Kim. Pseudorandom Functions with New Properties from Hard Lattice Problems. PhD thesis, 2021.
  43. The random oracle model: A twenty-year retrospective. Cryptology ePrint Archive, Paper 2015/140, 2015. https://eprint.iacr.org/2015/140.
  44. Separating adaptive streaming from oblivious streaming using the bounded storage model. In Advances in Cryptology - CRYPTO 2021 - 41st Annual International Cryptology Conference, CRYPTO, Proceedings, Part III, pages 94–121, 2021.
  45. P. Langley. Crafting papers on machine learning. In Pat Langley, editor, Proceedings of the 17th International Conference on Machine Learning (ICML 2000), pages 1207–1216, Stanford, CA, 2000. Morgan Kaufmann.
  46. Delving into transferable adversarial examples and black-box attacks. In 5th International Conference on Learning Representations, ICLR, Conference Track Proceedings, 2017.
  47. Towards deep learning models resistant to adversarial attacks. In 6th International Conference on Learning Representations, ICLR, Conference Track Proceedings, 2018.
  48. Keep that card in mind: Card guessing with limited memory. CoRR, abs/2107.03885, 2021.
  49. Hardness of sis and lwe with small parameters. Cryptology ePrint Archive, Paper 2013/069, 2013. https://eprint.iacr.org/2013/069.
  50. Multi-dimensional clustering: A new data layout scheme in DB2. In Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data, pages 637–641, 2003.
  51. Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Review, 52(3):471–501, 2010.
  52. Beating the folklore algorithm for dynamic matching. In 13th Innovations in Theoretical Computer Science Conference, ITCS, 2022.
  53. Access path selection in a relational database management system. In Proceedings of the 1979 ACM SIGMOD International Conference on Management of Data, pages 23–34. ACM, 1979.
  54. Storage estimation for multidimensional aggregates in the presence of hierarchies. In VLDB’96, Proceedings of 22th International Conference on Very Large Data Bases, pages 522–531, 1996.
  55. Adversarially robust generalization requires more data. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS., pages 5019–5031, 2018.
  56. Intriguing properties of neural networks. International Conference on Learning Representations, 2014.
  57. Ensemble adversarial training: Attacks and defenses. In 6th International Conference on Learning Representations, ICLR, Conference Track Proceedings, 2018.
  58. Compressed sensing of low-rank plus sparse matrices. ArXiv, abs/2007.09457, 2020.
  59. David Wajc. Rounding dynamic matchings against an adaptive adversary. In Proccedings of the 52nd Annual ACM SIGACT Symposium on Theory of Computing, STOC, pages 194–207, 2020.
  60. Tight bounds for adversarially robust streams and sliding windows via difference estimators. In 62nd IEEE Annual Symposium on Foundations of Computer Science, FOCS, pages 1183–1196, 2021.
Citations (1)

Summary

We haven't generated a summary for this paper yet.