5 papers
PrefixWall: Mitigating Prefix Caching Side Channels in Shared LLM Systems
Panagiotis Georgios Pennas, Konstantinos Papaioannou, Marco Guarnieri +1
Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previously computed states for the beginning pa…
Alignment Contracts for Agentic Security Systems
Isaac David, Marco Guarnieri, Arthur Gervais
Agentic security systems increasingly combine LLM planners with tools that can discover, validate, and report vulnerabilities. This creates an asymmetric control problem: the syste…
Detecting speculative leaks with compositional semantics
Xaver Fabian, Marco Guarnieri, Boris Köpf +4
Speculative execution enhances processor performance by predicting intermediate results and executing instructions based on these predictions. However, incorrect predictions can le…
Synthesis of Sound and Precise Leakage Contracts for Open-Source RISC-V Processors
Zilong Wang, Gideon Mohr, Klaus von Gleissenthall +2
Leakage contracts have been proposed as a new security abstraction at the instruction set architecture level. Leakage contracts aim to capture the information that processors may l…
AMuLeT: Automated Design-Time Testing of Secure Speculation Countermeasures
Bo Fu, Leo Tenenbaum, David Adler +7
In recent years, several hardware-based countermeasures proposed to mitigate Spectre attacks have been shown to be insecure. To enable the development of effective secure speculati…