mlsanityData to 7 Oct 2026

HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving

arXiv 2609.08306 ↗First posted 8 Sep 2026cs.CR cs.CL cs.LGcited by 0

On the map: Efficient LLM inference and serving → Serving systems and request scheduling

Abstract (arXiv)

We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated honeypot model, shielding production while the adversary's interaction is continuously harvested for intelligence. Existing defenses embed traps inside model memory or rebuild deception at the protocol layer, leaving the serving tier unprotected and feeding nothing back into detection. HoneyRoute couples (i) a streaming router (a frozen 0.8B-embedding backbone with per-domain MLP heads), (ii) a dual-implementation honeypot (a rule/prompt-engineered code honeypot or a dedicated same-family replica), and (iii) an analysis loop that converts trapped interactions into attacker fingerprints for router retraining. On a production trace plus a seven-domain attack corpus, the router reaches F1=.911 at 38 ms median added latency, matching 96% of a two-tier guard-LLM cascade's F1 at 1/385 of its latency with 0% evasion under 13 adversarial transformations; diverting the malicious share cuts production-model token consumption under concurrent flooding with real GCG-suffix payloads by 97.8%; the trained replica agrees with the production model on 92.9% of benign holdout requests, while naive unconditional bait injection collapses to 7.6% and selective camouflaged injection recovers to 88.9%, mapping the recoverable fidelity-traceability frontier; and a loop-trained correction head cuts misrouting of legitimate security research 9x while raising detection F1 to .933.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving. Builds on 23 of its 25 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

23 of 25 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  4. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  5. 2024RouteLLM: Learning to Route LLMs with Preference Datacited by 633
  6. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Modelscited by 494
  7. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 364
  8. 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identificationcited by 33
  9. 2023LLM in the Shell: Generative Honeypotscited by 19
  10. 2024LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wildcited by 12
  11. 2026HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defensecited by 6
  12. 2024HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large Language Modelcited by 5
11 more
  1. 2025LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generationcited by 3
  2. 2025VelLMes: A high-interaction AI-based deception frameworkcited by 3
  3. 2025SoK: Honeypots & LLMs, More Than the Sum of Their Parts?cited by 3
  4. 2025Active Honeypot Guardrail System: Probing and Confirming Multi-Turn LLM Jailbreakscited by 2
  5. 2025SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypotscited by 2
  6. 2026MemPot: Defending Against Memory Extraction Attack with Optimized Honeypotscited by 2
  7. 2026SingGuard-NSFA: Extensible Guardrails for Agentic AI via Generative Reasoning and Real-Time Classificationcited by 2
  8. 2026Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypotscited by 1
  9. 2026Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypotcited by 1
  10. 2026ShellGames: Speculative LLM-Driven SSH Deceptioncited by 1
  11. 2026AdvancedShelLM: A Stateful Multi-Agent LLM Honeypot for SSH Deceptioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Based Penetration Testing in the Presence of Honeypots ↗
  2. 2026Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
  3. 2026Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
  4. 2026RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
  5. 2025RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress
  6. 2026LLM Router: Rethinking Routing with Prefill Activations
  7. 2026Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades
  8. 2024BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models