Zhechang Zhang

Papers on Lattice

Total citations

Topics

Research focus

Constitutional AI & AI Ethics (1)Red-Teaming & Adversarial Robustness (1)Tool Use & Agents (1)

Frequent co-authors

Hengkai Ye (1)

Papers (1)

Apr 8, 2026

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Stop prompt injection attacks before they start: TRUSTDESC automatically generates verified tool descriptions from code, preventing LLMs from being tricked by malicious or misleading tool instructions.

Hengkai Ye, Zhechang Zhang

Constitutional AI & AI Ethics Red-Teaming & Adversarial Robustness Tool Use & Agents

Zhechang Zhang

Research focus

Frequent co-authors

Papers (1)

Search

Zhechang Zhang

Research focus

Frequent co-authors

Papers (1)