DeepAI AI Chat
Log In Sign Up

The Adversarial Robustness of Sampling

by   Omri Ben-Eliezer, et al.

Random sampling is a fundamental primitive in modern algorithms, statistics, and machine learning, used as a generic method to obtain a small yet "representative" subset of the data. In this work, we investigate the robustness of sampling against adaptive adversarial attacks in a streaming setting: An adversary sends a stream of elements from a universe U to a sampling algorithm (e.g., Bernoulli sampling or reservoir sampling), with the goal of making the sample "very unrepresentative" of the underlying data stream. The adversary is fully adaptive in the sense that it knows the exact content of the sample at any given point along the stream, and can choose which element to send next accordingly, in an online manner. Well-known results in the static setting indicate that if the full stream is chosen in advance (non-adaptively), then a random sample of size Ω(d / ε^2) is an ε-approximation of the full data with good probability, where d is the VC-dimension of the underlying set system (U,R). Does this sample size suffice for robustness against an adaptive adversary? The simplistic answer is negative: We demonstrate a set system where a constant sample size (corresponding to VC-dimension 1) suffices in the static setting, yet an adaptive adversary can make the sample very unrepresentative, as long as the sample size is (strongly) sublinear in the stream length, using a simple and easy-to-implement attack. However, this attack is "theoretical only", requiring the set system size to (essentially) be exponential in the stream length. This is not a coincidence: We show that to make Bernoulli or reservoir sampling robust against adaptive adversaries, the modification required is solely to replace the VC-dimension term d in the sample size with the cardinality term log |R|. This nearly matches the bound imposed by the attack.


page 1

page 2

page 3

page 4


A Framework for Adversarially Robust Streaming Algorithms

We investigate the adversarial robustness of streaming algorithms. In th...

Temporally-Biased Sampling for Online Model Management

To maintain the accuracy of supervised learning models in the presence o...

Stream Sampling with Immediate Decision

The manuscript introduces a method to select a random sample from a stre...

Temporally-Biased Sampling Schemes for Online Model Management

To maintain the accuracy of supervised learning models in the presence o...

Analysis of Noisy Evolutionary Optimization When Sampling Fails

In noisy evolutionary optimization, sampling is a common strategy to dea...

Relaxed Models for Adversarial Streaming: The Advice Model and the Bounded Interruptions Model

Streaming algorithms are typically analyzed in the oblivious setting, wh...

Pattern Recognition and Event Detection on IoT Data-streams

Big data streams are possibly one of the most essential underlying notio...