5 papers
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…
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…
KnowML: Improving Generalization of ML-NIDS with Attack Knowledge Graphs
Xin Fan Guo, Xinran Zheng, Albert Merono Penuela +3
Anomaly-based ML-NIDS (A-NIDS) model normal network behavior from benign data and classify deviations from this baseline as anomalies, theoretically enabling the detection of evolv…
Investigation of Advanced Persistent Threats Network-based Tactics, Techniques and Procedures
Almuthanna Alageel, Sergio Maffeis, Imperial College London
The scarcity of data and the high complexity of Advanced Persistent Threats (APTs) attacks have created challenges in comprehending their behavior and hindered the exploration of e…
Adaptive Experimental Design for Intrusion Data Collection
Kate Highnam, Zach Hanif, Ellie Van Vogt +3
Intrusion research frequently collects data on attack techniques currently employed and their potential symptoms. This includes deploying honeypots, logging events from existing de…