EUVIMEDEUVIMED entdecken
Crossref

IOLeak: Side-channel Information Leakage by Monitoring CPU Frequency Scaling through I/Os

Li Zhu, Siting Liu, Chundong Wang

ACM Transactions on Embedded Computing Systems · 16.07.2026

DOI: 10.1145/3830017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Embedded Computing Systems, online erschienen am 16.07.2026. Verfasst von Li Zhu und 2 weiteren Autor:innen. Die Arbeit nennt 91 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Power efficiency gains increasing importance to both general-purpose and embedded computing systems. CPU frequency scaling is widely used to dynamically adjust the speed and voltage of CPU cores in real time, aiming to gain both high performance and power efficiency. Prior works indicate that the runtime variations of CPU frequency expose a viable attack surface to leak information of the ongoing workload. In this paper, we find that the performance of I/O requests, such as file I/Os on a fast storage device, is affected by the runtime changes of CPU frequency and, in turn, is exploitable to speculate the workload’s sensitive information. We are hence motivated to develop IOLeak , a new side channel that is based on CPU frequency scaling but does not directly rely on CPU frequency values. We first build IOLeak covert channel by online monitoring I/O latency for secretive communication, both in noise-free and noisy environments. Next, we leverage IOLeak to launch a number of stealthy attacks, such as extracting cryptographic keys and fingerprinting websites, and confirm that IOLeak successfully leaks information by conducting inconspicuous file I/O operations. We particularly demonstrate that IOLeak is effective in the cross-virtual machine (VM) fashion that has not been covered by prior attacks relying on CPU frequency values. We also verify that IOLeak is capable in both general-purpose computers and embedded systems. These justify the serious security breach that IOLeak causes. Regarding the impact of IOLeak, we have responsibly reported our findings to the security teams of relevant organizations and received their feedback.

Zitieren

APA

Zhu, L., Liu, S., & Wang, C. (2026). IOLeak: Side-channel Information Leakage by Monitoring CPU Frequency Scaling through I/Os. ACM Transactions on Embedded Computing Systems. https://doi.org/10.1145/3830017

Vancouver

Zhu L, Liu S, Wang C. IOLeak: Side-channel Information Leakage by Monitoring CPU Frequency Scaling through I/Os. ACM Transactions on Embedded Computing Systems. 2026. doi:10.1145/3830017

BibTeX
@article{Zhu2026,
  author = {Zhu, Li and Liu, Siting and Wang, Chundong},
  title = {IOLeak: Side-channel Information Leakage by Monitoring CPU Frequency Scaling through I/Os},
  journal = {ACM Transactions on Embedded Computing Systems},
  year = {2026},
  doi = {10.1145/3830017}
}
Kostenlos starten →