Shawn Shan

TL;DR: This work intentionally injects trapdoors, honeypot weaknesses in the classification manifold that attract attackers searching for adversarial examples, and analytically proves that trapdoors shape the computation of adversarial attacks so that attack inputs will have feature representations very similar to those of trapdoors.

TL;DR: Tracking Transparency is presented, a privacy-preserving browser extension that visualizes examples of long-term, longitudinal information that third-party trackers could have inferred from users' browsing.

TL;DR: Both the sensitivity of the interest category and participants' actual interest in that topic significantly impacted their attitudes toward inferencing, and the results inform the design of transparency tools.

TL;DR: Blacklight is a new defense against black-box adversarial attacks that targets a key property of black- box attacks: to compute adversarial examples, they produce sequences of highly similar images while trying to minimize the distance from some initial benign input.