Physical Adversarial Examples for Object Detectors

Presented at the 12th USENIX Workshop on Offensive Technologies (WOOT ’18), this paper explores physical adversarial attacks for object detection models, a broader class of deep learning algorithms widely used to detect and label multiple objects within a scene.

Data Statements for NLP: Toward Mitigating System Bias and Enabling Better Science

In research published in Transactions of the Association for Computational Linguistics, experts in information science and computational linguistics investigate data statements as a practice to address critical ethical and scientific issues that result when systems developed with data from certain populations are used in systems with other populations.

SeaGlass: Enabling City-Wide IMSI-Catcher Detection

SeaGlass is a system designed by security researchers at the University of Washington to measure IMSI-catcher use across a city. The project aims to help communities maintain their privacy by building a community-driven, open data service to detect cellphone surveillance and produce high-quality cellular network data for research. This paper was published at Privacy Enhancing Technology Symposium 2017.

Computer Security, Privacy, and DNA Sequencing: Compromising Computers with Synthesized DNA, Privacy Leaks, and More

This paper evaluates the robustness of DNA processing tools if (or when) adversarial attacks manifest. We demonstrate, for the first time, the synthesis of DNA which — when sequenced and processed— gives an attacker arbitrary remote code execution. Informed by our experiments and results, we develop a broad framework and guidelines to safeguard security and privacy in DNA synthesis, sequencing, and processing. This paper was published at the 2017 USENIX Security Symposium.

Exploring ADINT: Using Ad Targeting for Surveillance on a Budget

In this work, we explore the following question: can third-parties use the purchasing of ads to extract private information about individuals? We find that the answer is yes. We also conduct a broad survey of other ad networks and assess their risks to similar attacks. We then step back and explore the implications of our findings. Published at the 16th ACM Workshop on Privacy in the Electronic Society (WPES 2017).

To Make a Robot Secure: An Experimental Analysis of Cyber Security Threats Against Teleoperated Surgical Robots

Rapidly growing applications of teleoperated robots raise the question; what if the computer systems for these robots are attacked, taken over and even turned into weapons? This paper seeks to answer this question by systematically analyzing possible cyber security attacks against an advanced teleoperated robotic surgery system, aiming to raise awareness and increase understanding of these emerging threats.

The Case for a Federal Robotics Commission

Published by Brookings, this paper is part of series focused on the future of civilian robotics, which seeks to answer the varied legal questions around the integration of robotics into human life.

Robotics and the Lessons of Cyberlaw

Two decades of analysis have produced a rich set of insights as to how the law should apply to the Internet’s peculiar characteristics. But, in the meantime, technology has not stood still. This article, published in the California Law Review, is the first to examine what the introduction of a new, equally transformative technology means for cyberlaw (and law in general).