uGen: An Agentic Framework for Generating Microarchitectural Attack PoCs

2026-05-14

AI Summary

This work addresses the high cost, expert dependency, and poor portability of proof-of-concept (PoC) development for microarchitectural attacks, which hinder systematic vulnerability assessment. To overcome these limitations, the authors propose uGen—the first large language model (LLM)-based framework for automated microarchitectural attack generation. uGen innovatively integrates retrieval-augmented generation (RAG) with a multi-agent collaboration mechanism to effectively compensate for the LLM’s knowledge gaps in critical attack primitives such as cache side channels and speculative execution. Evaluated across diverse microarchitectures, uGen achieves up to 100% success rate for Spectre-v1 and 80% for Prime+Probe attacks, generating each PoC in under four minutes at a cost as low as \$1.25, thereby substantially advancing the automation and scalability of microarchitectural exploit synthesis.

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 identifying attack-specific knowledge gaps in LLMs. Through a systematic study of state-of-the-art models (GPT, Claude, and Qwen3), we find that LLMs frequently misgenerate or misplace critical attack primitives. Guided by this analysis, uGen employs a retrieval-augmented, multi-agent design that injects missing domain knowledge to synthesize functionally correct microarchitectural attack PoCs tailored to defender requirements. We evaluate uGen on cache-based and speculative-execution attacks across diverse set of microarchitectures, vulnerable functions, and LLM platforms. In the deployment stage, uGen achieves up to 100% success rate for Spectre-v1 (Claude Sonnet-4) and 80% for Prime+Probe (Qwen3-Coder). Finally, we demonstrate that uGen can generate a successful PoC code with a cost of $1.25 in under four minutes.

Problem

• microarchitectural attacks
• vulnerability assessment
• attack code generation
• PoC portability
• automated exploitation

Innovation

• microarchitectural attacks
• LLM-driven framework
• retrieval-augmented generation
• automated PoC synthesis
• multi-agent design