← Search

Edward McFowland

2 accepted papers

2020

Detecting Adversarial Attacks via Subset Scanning of Autoencoder Activations and Reconstruction Error

IJCAI 2020poster

Reliably detecting attacks in a given set of inputs is of high practical relevance because of the vulnerability of neural networks to adversarial examples. These altered inputs create a security risk in applications with real-world consequences, such as self-driving cars, robotics and financial ser…

Cited by 0SourcePDFScholar
2018

Gaussian Process Subset Scanning for Anomalous Pattern Detection in Non-iid Data

AISTATS 2018poster

Identifying anomalous patterns in real-world data is essential for understanding where, when, and how systems deviate from their expected dynamics. Yet methods that separately consider the anomalousness of each individual data point have low detection power for subtle, emerging irregularities. Addit…

Cited by 0SourcePDFScholar