Latest

Last Week in GAI Security Research - 11/25/24

Last Week in GAI Security Research - 11/25/24

Highlights from Last Week * ๐Ÿฆนโ€โ™‚ RAG-Thief: Scalable Extraction of Private Data from Retrieval-Augmented Generation Applications with Agent-based Attacks * ๐Ÿ  Adapting to Cyber Threats: A Phishing Evolution Network (PEN) Framework for Phishing Generation and Analyzing Evolution Patterns using Large Language Models * ๐Ÿงต A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt
Brandon Dixon
Last Week in GAI Security Research - 11/18/24

Last Week in GAI Security Research - 11/18/24

Highlights from Last Week * ๐Ÿ‘น Unmasking the Shadows: Pinpoint the Implementations of Anti-Dynamic Analysis Techniques in Malware Using LLM * ๐Ÿ‘ LLM App Squatting and Cloning * โœ… Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders * ๐Ÿ’” RedCode: Risky Code Execution and Generation Benchmark for Code Agentsย  * ๐ŸŽ“ MultiKG: Multi-Source Threat Intelligence
Brandon Dixon