Poster: StreamToxWatch – Data Poisoning Detector in Distributed, Event-based Environments
Edmon Begoli · 2023
StreamToxWatch, or ToxWatch for short, is an early-stage ensemble architecture for data poisoning detection and monitoring in online learning systems over streams. Detecting data poisoning is difficult, especially in distributed streaming systems where statistical baselines change on the fly and across the system. For that reason, ToxWatch employs a combination of input, (adversarial) conceptual drift, and model performance monitors intended to observe anomalous behaviors and phenomena across the system and to offer targeted detection signals to downstream applications.