Author

Xing Zheng

h-index 3 View on Semantic Scholar

We have 6 of 10 papers

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.

Preprint Sep 2026

The Missing Boundary: How Autonomous Agents Lose Control

Autonomous agents increasingly perform long-horizon tasks involving tool use, persistent state, and consequential actions, raising a fundamental question: \emph{under what conditions does an agent cross the boundary of authorized execution while pursuing a legitimate task?} Existing studies often attribute such failure...

Zong-Hao Ying, Xiang-Fan Wu, Bo Yang et al. · 1 citation · ⚡1

Preprint Sep 2026

pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation

Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks (13 methods), channels (16 ca...

Zong-Hao Ying, Xiang-Fan Wu, Bo Yang et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Collective Loss of Control in LLM Agent Systems: An Epidemic Account of Mutation, Contagion, and Recovery

The account motivates complementary defenses: strengthen resistance and recovery alongside prevention of spontaneous deviations, and audit and restrict unintended communication paths that can turn local failures into collective loss of control.

Xiang-Fan Wu, Zong-Hao Ying, Hui-Yu Wu et al. · 0 citations

Preprint Aug 2026

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Skill evolution is revealed as a new attack surface and provenance-aware skill lifecycle protection is motivated to motivate provenance-aware skill lifecycle protection.

Zong-Hao Ying, Xiang-Fan Wu, Hui-Yu Wu et al. · 5 citations · ⚡1

Preprint Aug 2026

Security Assessment of DeepSeek Harness with A.I.G: Evaluating Resistance to Indirect Prompt Injection

This work assesses indirect prompt injection in DeepSeek Harness, using AI-Infra-Guard (A.I.G) to construct tests, deliver controlled taint, execute DSH, collect traces, and judge outcomes, and relates these results to DSH's treatment of tool results, additional contexts, and tool-call policy hooks.

Zong-Hao Ying, Xiang-Fan Wu, Hui-Yu Wu et al. · 2 citations

Preprint Aug 2026

Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs

AFL and EFL have little detectable route-level association with GPQA-Diamond accuracy and pronounced EFL coincides with a decline in Terminal-Bench pass rate as task exposure increases, a pattern may arise because correctness in long-horizon tasks is more sensitive to extreme fidelity loss.

Xiang-Fan Wu, Zong-Hao Ying, Hui-Yu Wu et al. · 1 citation