
Last Week in GAI Security Research - 03/31/25
Highlights from Last Week
* 🚒 Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts
* 📶 Large Language Models powered Network Attack Detection: Architecture, Opportunities and Case Study
* 🎭 Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation
* 🐠 EXPLICATE: Enhancing Phishing Detection through Explainable AI and LLM-Powered Interpretability