Shengfang Zhai
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2
Frequent co-authors
Research Timeline
2026
BadDLM: Backdooring Diffusion Language Models with Diverse Targets
The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across diverse targets.
Securing LLM Agents Need Intent-to-Execution Integrity
The paper proposes defining 'intent-to-execution integrity' as the necessary end-to-end correctness property for securing LLM agents, arguing that current defenses are insufficient due to untrusted components.
Highlighted terms show continued research focus across papers
Papers
cs.CRRecentMay 16, 2026
Securing LLM Agents Need Intent-to-Execution Integrity
Wenjie Qu, Ming Xu, Peiran Wang, Shengfang Zhai +2 more
The paper proposes defining 'intent-to-execution integrity' as the necessary end-to-end correctness property for securing LLM agents, arguing that current defenses are insufficient due to untrusted co…
View →
cs.CRRecentMay 10, 2026