Showing 2026 · cs.CRShow all
2 papers · 2 filters
cs.CR2026
Speedbumps: Rejection Attacks on Speculative Decoding
Adam Y. J. Jones, Yu Yuan, Sergio Maffeis
Speculative decoding is a popular technique for increasing the speed and reducing the costs of large language model (LLM) inference by verifying multiple draft tokens in a single t…
cs.CR2026
Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
Yannis Belkhiter, Giulio Zizzo, Sergio Maffeis +2
The growth of agentic AI has drawn significant attention to function calling Large Language Models (LLMs), which are designed to extend the capabilities of AI-powered system by inv…