Author

Xiang Li

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Review Oct 2026

ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?

Large language model (LLM) agents are increasingly used for vulnerability analysis, yet existing benchmarks provide limited coverage of exploitation that depends on interactions among network protocol components. Such vulnerabilities arise from inconsistencies in message interpretation, timing, state, or trust assumpti...

Fa-Sheng Miao, Zhao-Yu Hu, Xiang Li et al. · 0 citations

#artificial intelligence Preprint Oct 2026

Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers

TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer defines in advance and returns a probability for each answer. The vendor admits that adversarial input can change these answers but gives no numbers. In this paper, we present the first controlled adve...

Xiang Li, Ai-Chun Huang, Ming-Ming Zhang et al. · 0 citations

Book Open access Oct 2026

Poster: Detecting Intent Inconsistency in Mobile Apps:A Focus on Interaction Flow Contamination

The commercialization of the mobile Internet has driven many apps to adopt deceptive interaction designs (referred to as interaction flow contamination), which misalign system behaviors with user true intent and may harm user interests. Existing detection approaches suffer from semantic comprehension gaps, insufficient...

Jia-Lu Li, Xiang Li · Proceedings of the 2026 ACM... · 0 citations