Lattice AI Research

Research focus

Red-Teaming & Adversarial Robustness (2)Code Generation & Program Synthesis (1)Tool Use & Agents (1)

Frequent co-authors

Yuchen Chen (1)Weisong Sun (1)Haocheng Huang (1)Yuan Xiao (1)

Papers (2)

Jun 9, 2026

Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models

Natural backdoors in CodeLMs are not just a theoretical concern; they are prevalent and can undermine security across multiple code intelligence tasks.

Yuchen Chen, Weisong Sun, Haocheng Huang +11

Code Generation & Program Synthesis Red-Teaming & Adversarial Robustness

Jun 7, 2026

3d ago·also Tsinghua AI, PolyU, UMacau

Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems

Eight unique vulnerabilities threaten the integrity of LLM-driven data agents, exposing critical weaknesses in enterprise analytics systems.

Kuncan Wang, Ziting Wang, Peizhuo Lv +3

Red-Teaming & Adversarial Robustness Tool Use & Agents

Search

Peizhuo Lv

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)