arXiv (Cornell University) · 2016 · 236 citations · 39 references
ComputingComputer EngineeringComputer ScienceComputer SecurityHardware SecurityMalware AnalysisBinary ExploitationBranch PredictionMicroarchitectural SecuritySide-channel AnalysisSide-channel AttacksBranch Misprediction PenaltyMicroarchitectural Side-channel AnalysisMicroarchitectural Side-channel AttacksSide-channel Attack MitigationSide-channel Attack ResistanceSide-channel ResistanceTiming Side-channel AnalysisVulnerability Exploitation Techniques
Intel SGX fails to clear branch history when exiting enclave mode, exposing fine‑grained control‑flow traces via a branch‑prediction side channel. This work investigates a novel branch‑shadowing side‑channel attack that can reveal each enclave branch and seeks to overcome practical obstacles to its exploitation. We devise two exploitation techniques—Intel PT/LBR‑based history inference and APIC‑based execution control—to bypass timing inaccuracies and enforce fine‑grained execution, and we evaluate hardware‑history‑clearing and propose the Zigzagger countermeasure. The attack successfully breaks ORAM, Sanctum, SGX‑Shield, and T‑SGX, and our study shows branch‑history clearing is viable while Zigzagger effectively mitigates the threat.
In this paper, we explore a new, yet critical, side-channel attack against Intel Software Guard Extension (SGX), called a branch shadowing attack, which can reveal fine-grained control flows (i.e., each branch) of an enclave program running on real SGX hardware. The root cause of this attack is that Intel SGX does not clear the branch history when switching from enclave mode to non-enclave mode, leaving the fine-grained traces to the outside world through a branch-prediction side channel. However, exploiting the channel is not so straightforward in practice because 1) measuring branch prediction/misprediction penalties based on timing is too inaccurate to distinguish fine-grained control-flow changes and 2) it requires sophisticated control over the enclave execution to force its execution to the interesting code blocks. To overcome these challenges, we developed two novel exploitation techniques: 1) Intel PT- and LBR-based history-inferring techniques and 2) APIC-based technique to control the execution of enclave programs in a fine-grained manner. As a result, we could demonstrate our attack by breaking recent security constructs, including ORAM schemes, Sanctum, SGX-Shield, and T-SGX. Not limiting our work to the attack itself, we thoroughly studied the feasibility of hardware-based solutions (e.g., branch history clearing) and also proposed a software-based countermeasure, called Zigzagger, to mitigate the branch shadowing attack in practice.
39
Thomas Ristenpart, Eran Tromer, Hovav Shacham et al. · 2009 · 2K citations
Cross-VM side channels and their use to extract private keys
Yinqian Zhang, Ari Juels, Michael K. Reiter et al. · 2012 · 785 citations
Fan Zhang, Ethan Cecchetti, Kyle Croman et al. · 2016 · 565 citations · Full text