uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs
Debopriya Roy Dipta, Thore Tiemann, Eduard Marin, Thomas Eisenbarth, Berk Gulmezoglu

TL;DR
uGen is an innovative framework leveraging large language models to automatically generate functional microarchitectural attack code, improving vulnerability testing efficiency and accuracy.
Contribution
It introduces uGen, the first LLM-driven system for automated attack code generation, addressing knowledge gaps with a retrieval-augmented, multi-agent approach.
Findings
uGen achieves up to 100% success rate for Spectre-v1 attacks.
uGen attains 80% success rate for Prime+Probe attacks.
A PoC can be generated in under four minutes at a cost of $1.25.
Abstract
Microarchitectural attacks continue to evolve, uncovering new exploitation vectors in modern processors. From a defensive perspective, assessing a system's susceptibility to such attacks remains challenging. Developing functional attack implementations is labor-intensive, requires deep microarchitectural expertise, and is highly sensitive to execution environments. Consequently, existing attacks often lack portability, limiting systematic and scalable vulnerability assessment. Recent advances in large language models (LLMs) suggest a potential avenue for lowering these barriers. However, it remains unclear whether LLMs can reliably generate functionally correct microarchitectural attack code suitable for rigorous vulnerability testing. In this work, we present uGen, the first LLM-driven framework for automated microarchitectural attack code generation. A key challenge we address is…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
