Author

Jun Wen Leong

h-index 2 View on Semantic Scholar

We have 3 of 4 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 Aug 2026

Instruction Self-Arbitration Is Not a Trust Boundary: Configuration-Dependent Tool Calls and External Enforcement in LLM Agents

LLM agents receive instructions from system prompts, users, memory and tools, and labels inside a shared context are not an enforceable trust boundary. We study how measurement and configuration choices change what benign file-deletion tasks on gateway-labelled endpoints appear to show (an availability-selected roster)...

Jun Wen Leong · 1 citation

#machine learning Preprint Jun 2026

Retrieval Observability Bounds on Provenance Detection for Agent Memory Poisoning: Measured Coverage and a Falsified Standalone Detector

This work formalises this as a framework-agnostic retrieval-to-action provenance graph, classify published attack families by their position relative to it, measure the resulting coverage property against collected agent traces, and falsify the detector's standalone deployment, reversing its own earlier recommendation...

Jun Wen Leong · 2 citations

Preprint Aug 2026

Recognition Without Enforcement: Configuration-Dependent Failures in LLM Agent Instruction Arbitration and External Control

This work treats model self-arbitration as a capability rather than a security boundary and implements an external reference monitor combining authenticated source routing with capability-gated tool execution, deterministically rejects all tested forged, tampered, replayed, and unsigned requests while preserving legiti...

Jun Wen Leong · 0 citations