We are delighted to announce that Jaron Mink will give a talk here at TeamUSEC on Thursday the 28th. The talk will be held online in English and all are more than welcome to attend.

Abstract: Machine learning models are becoming increasingly powerful and are actively deployed in security- and privacy-critical systems; however, this shift has inevitably led to abusive machine learning applications and the exploitation of machine learning vulnerabilities which are lucrative for adversaries and harmful to users. Many of these victims, such as social media users and machine learning practitioners, are attempting to understand and navigate these security and privacy threats for the first time, requiring adjustments in their behavior and responsibilities.

In this talk, I will discuss how end-users and machine learning practitioners perceive and mitigate the emerging machine learning-enabled threats they now face. Specifically, I will discuss how end-users perceive and respond to friend requests from deepfake social media profiles, and the barriers machine learning practitioners have towards implementing defenses against adversarial machine learning threats. Through these works, I will discuss how mitigations may require the changing of various human roles and open areas of investigations.

Short Bio

Jaron Mink is a PhD Candidate of the Computer Science Department at University of Illinois at Urbana-Champaign. He received his Bachelor of Science (Magna Cum Laude) in the field of Computer Science at University of California, Los Angeles in 2019. Jaron investigates computer security and privacy threats and focuses on users’ perception and mitigation of emerging concerns. His work has appeared in venues such as CHI, USENIX Security, IEEE S&P, WWW, and has been reported on by the Scientific American news organization. He is an awardee of the NSF Graduate Research Fellowship Program (GRFP). Jaron also serves as a consultant, investigating ways to better anticipate AI safety risks. He has spent two summers working with faculty at the Max Planck Institute for Security and Privacy (2021) and the Max Planck Institute for Software Systems (2022).