# Understanding Implicit Trust Errors in Core Carrier Networks through Multi-Agent Flaw Discovery and Analysis

arXiv: https://arxiv.org/abs/2607.10315 · HTML: https://mlsanity.com/paper/2607.10315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 60 references that are in the map.
- First posted on arXiv 11 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Evaluating Fuzz Testing](https://mlsanity.com/paper/1808.09700/) (2018)
- [From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs](https://mlsanity.com/paper/2509.01835/) (2025)
- [Synthesizing Multi-Agent Harnesses for Vulnerability Discovery](https://mlsanity.com/paper/2604.20801/) (2026)
- [MulVul: Retrieval-augmented Multi-Agent Code Vulnerability Detection via Cross-Model Prompt Evolution](https://mlsanity.com/paper/2601.18847/) (2026)
- [StateAFL: Greybox Fuzzing for Stateful Network Servers](https://mlsanity.com/paper/2110.06253/) (2021)
- [Hermes: Unlocking Security Analysis of Cellular Network Protocols by Synthesizing Finite State Machines from Natural Language Specifications](https://mlsanity.com/paper/2310.04381/) (2023)
- [BaseSAFE: Baseband SAnitized Fuzzing through Emulation](https://mlsanity.com/paper/2005.07797/) (2020)
- [CellularLint: A Systematic Approach to Identify Inconsistent Behavior in Cellular Network Specifications](https://mlsanity.com/paper/2407.13742/) (2024)
- [Multi-Agent Taint Specification Extraction for Vulnerability Detection](https://mlsanity.com/paper/2601.10865/) (2026)
- [Stateful Greybox Fuzzing](https://mlsanity.com/paper/2204.02545/) (2022)
- [Cloud-native 5G experimental platform with over-the-air transmissions and end-to-end monitoring](https://mlsanity.com/paper/2207.11936/) (2022)
- [CellSecInspector: Safeguarding Cellular Networks via Automated Security Analysis on Specifications](https://mlsanity.com/paper/2512.24682/) (2025)

## Abstract (arXiv)

Cellular core networks (CNs) are critical infrastructure, yet their internal security model has historically relied on physical isolation: interfaces between core components often operate within an assumed trust zone. As CNs transition to cloud-native deployments, this assumption weakens, expanding the attack surface and enabling external adversaries to reach previously internal interfaces. From a root-cause analysis of security flaws reported in GitHub issues for opensource CN implementations, we found a recurring pattern of blind trust among CN components. Components may omit syntactic validation, fail to enforce semantic invariants, or allocate resources without checking availability. Once internal interfaces become reachable, these weaknesses can lead to severe impacts such as denial of service and session hijacking. We call these vulnerabilities implicit trust errors (iTrue). To detect iTrues and understand their security impacts, we designed iFinder, an LLM-driven multi-agent system that summarizes known flaws, distills them into detection patterns, and applies them to discover new iTrues in CN implementations. To suppress hallucinations produced by large language models (LLMs), we built an innovative strategy that crosschecks both 3GPP specifications and CN code to capture existing protection missed by the agents. Further, we developed a technique that uses LLMs to generate proof-of-concept (PoC) exploits for potential iTrues and iteratively refine the PoCs by automatically executing them against CN implementations and analyzing results. Running iFinder on seven prominent open-source CN implementations, we discovered 84 previously unknown vulnerabilities. Among them, 83 have already been confirmed and 81 have been assigned CVEs. Importantly, a session-hijacking flaw has been confirmed on real-world commercial 5G core networks.