Abstract: Reversible Adversarial Examples (RAE) are designed to protect the intellectual property of datasets. Such examples can function as imperceptible adversarial examples to erode the model ...

Abstract: Identifying hidden anomalous behavior is a major challenge in anomaly detection, particularly in complex systems where anomalies are buried within massive log data and cannot be easily ...

A new online program in the Boston College School of Social Work is designed to prepare students to work in the humanitarian aid and development sectors, helping to improve the lives of the world’s ...