Xinhang Ma

Identifiers

• name variant Xinhang Ma 0.60 · backfill

Papers (2)

1. AutoDojo: Adaptive Black-Box Attacks Reveal the Limits of IPI Defenses and Task-Specification Effects in LLM Agents cs.CR · 2026 · author #1
2. Protecting Language Models Against Unauthorized Distillation through Trace Rewriting cs.AI · 2026 · author #1

Mentions

• 2606.15057 #1 · arxiv_oai · confidence 0.70 Xinhang Ma

Frequent Coauthors

• Ning Zhang 2 shared papers
• Yevgeniy Vorobeychik 2 shared papers
• Chaowei Xiao 1 shared papers
• Taoran Li 1 shared papers
• William Yeoh 1 shared papers
• Zhiyuan Yu 1 shared papers