Context-Sensitive Fencing: Securing Speculative Execution via Microcode Customization
By Mohammadkazem Taram, Ashish Venkat, Dean M. Tullsen. 2019
120 citations recorded by the source corpus.
This paper describes context-sensitive fencing (CSF), a microcode-level defense against multiple variants of Spectre. CSF leverages the ability to dynamically alter the decoding of the instruction stream, to seamlessly inject new micro-ops, including fences, only when dynamic conditions indicate they are needed. This enables the processor to protect against the attack, but with minimal impact on the efficacy of key performance features such as speculative execution. This research also examines several alternative fence implementations, and introduces three new types of fences which allow most dynamic reorderings of loads and stores, but in a way that prevents speculative accesses from changing visible cache state. These optimizations reduce the performance overhead of the defense mechanism, compared to state-of-the-art software-based fencing mechanisms by a factor of six.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hadi Esmaeilzadeh
- Fatemehsadat Mireshghallah
- Prakash Ramrakhyani
- Mohammadkazem Taram
- Dean M. Tullsen
In Electrical and Electronic Engineering
- Hadi Esmaeilzadeh
- Prakash Ramrakhyani
- Fatemehsadat Mireshghallah
- Mohammadkazem Taram
- Dean M. Tullsen
- Sparsh Mittal
In Signal Processing
- Hadi Esmaeilzadeh
- Prakash Ramrakhyani
- Fatemehsadat Mireshghallah
- Mohammadkazem Taram
- Dean M. Tullsen
Citations in the corpus
- Privacy in Deep Learning: A Survey (2020, neutral): “This execution model, however, requires the users to send their data to an enclave running on remote servers which allows the remote server to have access to the raw data and as the new breaches in hardware [32, 31, 128, 129, 130, 131] show, the access can lead to comprised privacy.”
- Shredder: Learning Noise to Protect Privacy with Partial DNN Inference on the Edge (2019, methodology): “In contrast to Shredder, this model still allows the remote server to have access to the raw data and as the new breaches in hardware [1, 2, 61, 62, 63, 64] show, the access can lead to comprised privacy.”
- Shredder: Learning Noise Distributions to Protect Inference Privacy (2019, methodology): “ers to send their data to an enclave running on a remote servers. In contrast to Shredder, this model still allows the remote server to have access to the raw data and as the new breaches in hardware [1, 2, 61, 62, 63, 64] show, the access can lead to comprised privacy. Differential privacy. As a ma”