# Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Mining

arXiv: https://arxiv.org/abs/2009.09497 · HTML: https://mlsanity.com/paper/2009.09497/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2020.

## Built on by (most cited first, 12 of 12)

- [Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectives](https://mlsanity.com/paper/2307.01390/) (2023)
- [Performative Drift Resistant Classification Using Generative Domain Adversarial Networks](https://mlsanity.com/paper/2504.01135/) (2025)
- [ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection](https://mlsanity.com/paper/2507.08597/) (2025)
- [When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems](https://mlsanity.com/paper/2607.06807/) (2026)
- [Employing chunk size adaptation to overcome concept drift](https://mlsanity.com/paper/2110.12881/) (2021)
- [From XAI to MLOps: Explainable Concept Drift Detection with Profile Drift Detection](https://mlsanity.com/paper/2412.11308/) (2024)
- [Fake or Real: The Impostor Hunt in Texts for Space Operations](https://mlsanity.com/paper/2507.13508/) (2025)
- [Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers](https://mlsanity.com/paper/2510.09294/) (2025)
- [Knowledge-Integrated Representation Learning for Crypto Anomaly Detection under Extreme Label Scarcity; Relational Domain-Logic Integration with Retrieval-Grounded Context and Path-Level Explanations](https://mlsanity.com/paper/2601.12839/) (2026)
- [Adversarial Vulnerability Under Temporal Concept Drift: A Longitudinal Study of Android Malware Detection](https://mlsanity.com/paper/2605.23623/) (2026)
- [TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers](https://mlsanity.com/paper/2608.23763/) (2026)
- [Feature-Context Consistency: Unsupervised Adversarial Detection with Drift Stability on Attributed Graphs](https://mlsanity.com/paper/2610.16694/) (2026)

## Abstract (arXiv)

Continuous learning from streaming data is among the most challenging topics in the contemporary machine learning. In this domain, learning algorithms must not only be able to handle massive volumes of rapidly arriving data, but also adapt themselves to potential emerging changes. The phenomenon of the evolving nature of data streams is known as concept drift. While there is a plethora of methods designed for detecting its occurrence, all of them assume that the drift is connected with underlying changes in the source of data. However, one must consider the possibility of a malicious injection of false data that simulates a concept drift. This adversarial setting assumes a poisoning attack that may be conducted in order to damage the underlying classification system by forcing adaptation to false data. Existing drift detectors are not capable of differentiating between real and adversarial concept drift. In this paper, we propose a framework for robust concept drift detection in the presence of adversarial and poisoning attacks. We introduce the taxonomy for two types of adversarial concept drifts, as well as a robust trainable drift detector. It is based on the augmented Restricted Boltzmann Machine with improved gradient computation and energy function. We also introduce Relative Loss of Robustness - a novel measure for evaluating the performance of concept drift detectors under poisoning attacks. Extensive computational experiments, conducted on both fully and sparsely labeled data streams, prove the high robustness and efficacy of the proposed drift detection framework in adversarial scenarios.