Key result
ECG, an LLM-empowered Embedded OS fuzzer, uncovered 32 new vulnerabilities and improved kernel code coverage by an average of 16.02% compared to existing fuzzers.
Why the study?
Embedded operating systems are much less tested for bugs than general-purpose operating systems, and fuzzing them encounters roadblocks due to poorly documented specifications and ineffectiveness in generating high-quality payloads.
ECG demonstrates enhanced capability in uncovering vulnerabilities in embedded operating systems using LLM-based corpus generation.
Answers are grounded in this paper and cite their sources.
ECG may aid embedded OS vulnerability detection; leaves open translation to medical device security.
Embedded operating systems (Embedded OSs) power much of our critical infrastructure but are, in general, much less tested for bugs than general-purpose operating systems. Fuzzing Embedded OSs encounter significant roadblocks due to much less documented specifications, an inherent ineffectiveness in generating high-quality payloads. In this article, we propose ECG, an Embedded OS fuzzer empowered by large language models (LLMs) to sufficiently mitigate the aforementioned issues. ECG approaches fuzzing Embedded OS by automatically generating input specifications based on readily available source code and documentation, instrumenting and intercepting execution behavior for directional guidance information, and generating inputs with payloads according to the pregenerated input specifications and directional hints provided from previous runs. These methods are empowered by using an interactive refinement method to extract the most from LLMs while using established parsing checkers to validate the outputs. Our evaluation results demonstrate that ECG uncovered 32 new vulnerabilities across three popular open-source Embedded OS (RT-Linux, RaspiOS, and OpenWrt) and detected ten bugs in a commercial Embedded OS running on an actual device. Moreover, compared to Syzkaller, Moonshine, KernelGPT, Rtkaller, and DRLF, ECG has achieved additional kernel code coverage improvements of 23.20%, 19.46%, 10.96%, 15.47%, and 11.05%, respectively, with an overall average improvement of 16.02%. These results underscore ECG’s enhanced capability in uncovering vulnerabilities, thus contributing to the overall robustness and security of the Embedded OS.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2024) studied Embedded OS vulnerabilities. ECG (LLM-empowered Embedded OS fuzzer) vs. Syzkaller, Moonshine, KernelGPT, Rtkaller, and DRLF was evaluated on Vulnerabilities uncovered and kernel code coverage. ECG, an LLM-empowered Embedded OS fuzzer, uncovered 32 new vulnerabilities and improved kernel code coverage by an average of 16.02% compared to existing fuzzers.
Synapse has enriched 10 related papers. Consider them for comparative context: