BruinSec Lab

Electrical and Computer Engineering · Computer Science

University of California, Los Angeles

BruinSec Lab, led by Prof. Yuan Tian at UCLA, studies the security, privacy, and safety of modern and emerging systems — from AI models and agents to IoT, voice platforms, and extended reality. We combine program analysis, protocol analysis, machine learning, and human factors, and publish at IEEE S&P, USENIX Security, CCS, NDSS, ICLR, and ICML.

Research Publications People News Join Us
Anime illustration: four bear researchers in blue-and-gold hoodies defend AI agents, private data and smart-home devices from a rooftop lab overlooking the UCLA campus at dusk.

News

All news →

Research at a glance

AI Security

We investigate the security and trustworthiness of machine learning models, including adversarial attacks, data poisoning, backdoor attacks on model merging, and environmental injection attacks on AI agents.

EIA (ICLR '25)BadMerging (CCS '24)Chimera (USENIX Sec '25)SoK: Vulnerability Repair (USENIX Sec '25)Poisoning Attacks (ICML '21)

Data Privacy

We study privacy risks and compliance, including GDPR enforcement, personal information disclosure in online communities, location privacy in recommendation systems, and user perceptions of data collection.

GDPR Consent (S&P '26)Smart Home IFA (PETS '26)City-wide WiFi (PETS '25)CHKPLUG (NDSS '23)SenRev (PETS '23)

System Security

We analyze the security of software systems including voice-controlled platforms, IoT ecosystems, authentication protocols, smart home automations, and extended reality (XR).

XR Threats (NDSS '26)Waltzz (USENIX Sec '25)AuthSaber (CCS '24)Alexa Skill Vetting (ICSE '24)TKPERM (NDSS '20)

What we are building

Active AI AgentsWeb Security

Bruinweb

Our team in the Amazon Nova AI Challenge: Trusted Software Agents — one of 10 international teams selected in 2026.

News
Active AI SecurityAgents

Trustworthy AI Agents

Research on safe and trustworthy AI agents, supported by Coefficient Giving, with Kai-Wei Chang, Cho-Jui Hsieh, and Nanyun Peng.

News
Active AI SecurityHealthcare

Trustworthy Medical AI

NSF-supported research on making medical AI systems secure and trustworthy.

News

Highlighted papers