Merge pull request #9 from tracebit-com/codex/add-reference-to-ai-conflict-article

Add Paper - Deception and Detection (International Security 2026)

Author: andy-smith-tracebit

README.MD

@@ -55,6 +55,7 @@ An awesome collection of articles, papers, conferences, guides, and tools relati
 - [HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense](https://arxiv.org/abs/2601.04034) (2026) - proposes a deceptive LLM defense framework with multi-agent coordination, plus a progressive jailbreak dataset and new metrics for measuring misdirection and attacker cost. 
 - [Measuring the Efficacy of Cyber Deception](https://www.techrxiv.org/doi/full/10.36227/techrxiv.176834017.70221537) (2026) - examines how to measure cyber deception effectiveness by reviewing existing evaluation approaches and proposing new metrics and frameworks to assess deceptive tactics in modern, AI-augmented threat environments.
 - [Q-Cowrie: Reinforcement Learning for Adaptive Honeypot Deception](https://link.springer.com/article/10.1007/s10207-026-01221-5) (2026) - presents “Q-Cowrie,” a reinforcement learning-enhanced Cowrie honeypot that models attacker decisions with an MDP and adapts responses during attacker interaction.
+- [Deception and Detection: Why Artificial Intelligence Empowers Cyber Defense over Offense](https://direct.mit.edu/isec/article/50/3/86/135683/Deception-and-Detection-Why-Artificial) (2026) - argues that AI automation benefits cyber defense more than offense, widening an offense-defense automation gap as stakes increase.
 
 ### Code Repositories
 - [Evaluating Deception and Moving Target Defense with Network Attack Simulation](https://github.com/dfki-in-sec/NASIM-MTD)