TY - GEN
T1 - Poster
T2 - 17th ACM International Conference on Distributed and Event-based Systems, DEBS 2023
AU - Begoli, Edmon
N1 - Publisher Copyright:
© 2023 Owner/Author(s).
PY - 2023/6/27
Y1 - 2023/6/27
N2 - 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.
AB - 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.
KW - concept drift
KW - data poisoning
KW - event processing
KW - stream processing
UR - http://www.scopus.com/inward/record.url?scp=85170037003&partnerID=8YFLogxK
U2 - 10.1145/3583678.3603282
DO - 10.1145/3583678.3603282
M3 - Conference contribution
AN - SCOPUS:85170037003
T3 - DEBS 2023 - Proceedings of the 17th ACM International Conference on Distributed and Event-based Systems
SP - 182
EP - 184
BT - DEBS 2023 - Proceedings of the 17th ACM International Conference on Distributed and Event-based Systems
PB - Association for Computing Machinery, Inc
Y2 - 27 June 2023 through 30 June 2023
ER -