Lattice AI Research

Research focus

Constitutional AI & AI Ethics (1)Multimodal Models (1)Open-Source Models & Weights (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Tao Ni (1)Zehua Sun (1)Wei-Bin Lee (1)Cong Wang (1)

Papers (2)

Jun 9, 2026

NUS2d ago·also HKU, KAUST

When VR Meets BCI: (Un)Observable Brainwave-aware Privacy Reconstruction in the Metaverse via Unrestricted Inbuilt Motion Sensors

Uncovering that VR motion sensors can reconstruct unobservable brainwave data reveals a critical privacy vulnerability in the Metaverse.

Tao Ni, Zehua Sun, Qingchuan Zhao +2

Constitutional AI & AI Ethics Multimodal Models

Apr 23, 2026

Zihan Wang +4Apr 23, 2026

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

LLM agents can have their proprietary skills stolen with just 3 interactions, exposing a major copyright vulnerability in the burgeoning skill marketplace.

Zihan Wang, Yu Liu, Chi Liu +2

Open-Source Models & Weights Red-Teaming & Adversarial Robustness Tool Use & Agents

Search

Qingchuan Zhao

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)