Advanced profiling for probabilistic Prime+Probe attacks and covert channels in ScatterCache
August 09, 2019 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Antoon Purnal, Ingrid Verbauwhede
arXiv ID
1908.03383
Category
cs.CR: Cryptography & Security
Citations
32
Venue
arXiv.org
Last Checked
6 months ago
Abstract
Timing channels in cache hierarchies are an important enabler in many microarchitectural attacks. ScatterCache (USENIX 2019) is a protected cache architecture that randomizes the address-to-index mapping with a keyed cryptographic function, aiming to thwart the usage of cache-based timing channels in microarchitectural attacks. In this note, we advance the understanding of the security of ScatterCache by outlining two attacks in the noise-free case, i.e. matching the assumptions in the original analysis. As a first contribution, we present more efficient eviction set profiling, reducing the required number of observable victim accesses (and hence profiling runtime) by several orders of magnitude. For instance, to construct a reliable eviction set in an 8-way set associative cache with 11 index bits, we relax victim access requirements from approximately $2^{25}$ to less than $2^{10}$ . As a second contribution, we demonstrate covert channel profiling and transmission in probabilistic caches like ScatterCache. By exploiting arbitrary collisions instead of targeted ones, our approach significantly outperforms known covert channels (e.g. full-cache eviction).
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Cryptography & Security
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
The Limitations of Deep Learning in Adversarial Settings
R.I.P.
π»
Ghosted
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
R.I.P.
π»
Ghosted
Spectre Attacks: Exploiting Speculative Execution
R.I.P.
π»
Ghosted
How To Backdoor Federated Learning
R.I.P.
π»
Ghosted
Evasion Attacks against Machine Learning at Test Time
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted