Scholar

Brian Jay Tang

Google Scholar ID: pgkhBk8AAAAJ

University of Michigan - Ann Arbor

Security and PrivacyArtificial IntelligenceHuman Computer Interaction

Citations & Impact

All-time

Citations

185

H-index

i10-index

Publications

Co-authors

Contact

Resume

Academic Achievements

"Ads that Talk Back": Implications and Perceptions of Injecting Personalized Advertising into LLM Chatbots, Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Navigating Cookie Consent Violations Across the Globe, 34th USENIX Security Symposium (2025)
Analyzing Privacy Implications of Data Collection in Android Automotive OS, ArXiv Preprint
Short: Achieving the Safety and Security of the End-to-End AV Pipeline, 1st Cyber Security in Cars Workshop (CSCS) at CCS
Steward: Natural Language Web Automation, ArXiv Preprint
Eye-Shield: Real-Time Protection of Mobile Device Screen Information from Shoulder Surfing, 32nd USENIX Security Symposium (2023)

Research Experience

Past research projects involved creating real-time systems, training LLMs & VLMs, analyzing privacy policies with NLP, and creating adversarial ML attacks on face recognition systems. Currently researching vision-language models and their security and privacy challenges, and creating large-scale data collection pipelines for training VLMs.

Education

Ph.D. Candidate, University of Michigan CSE. Advisor: Kang G. Shin. Undergraduate work at WI-PI with Kassem Fawaz, Varun Chandrasekaran, and Somesh Jha.

Background

Research Interests: Security & Privacy, AI Systems, Surveillance. Background: Primarily works on AI safety, security, and real-time systems.

Miscellany