Let’s Not Speculate: Discovering and Analyzing Speculative Execution Attacks

Speculative execution attacks exploit vulnerabilities at a CPU’s microarchitectural level, which, until recently, remained hidden below the instruction set architecture, largely undocumented by CPU vendors. New speculative execution attacks are released on a monthly basis, showing how aspects of the so-far unexplored microarchitectural attack surface can be exploited. In this paper, we generalize speculative execution related attacks and identify common components. The structured approach that we employed helps us to identify potential new variants of speculative execution attacks. We explore one such variant, SPLITSPECTRE, in depth and demonstrate its applicability to a real-world scenario with the SpiderMonkey JavaScript engine. Further, we introduce SPECULATOR, a novel tool to investigate speculative execution behavior critical to these new microarchitectural attacks. We also present our findings on multiple CPU platforms.

By: Andrea Mambretti, Matthias Neugschwandtner, Alessandro Sorniotti, Engin Kirda, William Robertson, Anil Kurmus

Published in: RZ3933 in 2018

LIMITED DISTRIBUTION NOTICE:

This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.

RZ3933.pdf

Questions about this service can be mailed to reports@us.ibm.com .