Yuan Hong

Papers on Lattice

Total citations

Topics

Research focus

Red-Teaming & Adversarial Robustness (2)Multimodal Models (1)Code Generation & Program Synthesis (1)Eval Frameworks & Benchmarks (1)

Frequent co-authors

Qin Yang (1)Lu Malloy (1)Joshua Lee (1)Xiaohan Chang (1)Meisam Mohammady (1)Shenao Yan (1)Shimaa Ahmed (1)Shan Jin (1)

Papers (2)

Jun 8, 2026

Qin Yang +5Jun 8, 2026

What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks

Typographic tricks can make harmful content invisible to AI while still being recognized by humans, exposing a major flaw in current moderation systems.

Qin Yang, Lu Malloy, Joshua Lee +3

Multimodal Models Red-Teaming & Adversarial Robustness

Mar 17, 2026

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

CodeScan achieves 97%+ accuracy in detecting data poisoning attacks in code generation LLMs by identifying structural similarities across generations, even when semantics are expressed in diverse syntactic forms.

Shenao Yan, Shimaa Ahmed, Shan Jin +2

Code Generation & Program Synthesis Eval Frameworks & Benchmarks Red-Teaming & Adversarial Robustness

Yuan Hong

Research focus

Frequent co-authors

Papers (2)

Search

Yuan Hong

Research focus

Frequent co-authors

Papers (2)