Wei Yang Bryan Lim

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Red-Teaming & Adversarial Robustness (2)Tool Use & Agents (2)

Frequent co-authors

Che Wang (2)Che Wang (2)Jiaming Zhang (2)Jiaming Zhang (2)

Papers (2)

Feb 24, 2026

2w ago

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

LLM agents can now defend against indirect prompt injection attacks without sacrificing task performance, thanks to a new method that surgically manipulates attention based on latent space analysis.

Che Wang, Che Wang, Fuyao Zhang +10

Red-Teaming & Adversarial Robustness Tool Use & Agents

2w ago

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

Agentic LLMs are far more vulnerable to indirect prompt injection attacks than previously thought: AdapTools achieves over 2x improvement in attack success while significantly degrading system utility, even against strong defenses.

Che Wang, Che Wang, Jiaming Zhang +11