CATalyst: Defeating last-level cache side channel attacks in cloud computing

By Fangfei Liu, Qian Ge, Yuval Yarom, Francis X. McKeen, Carlos V. Rozas, Gernot Heiser, Ruby B. Lee. International Symposium on High-Performance Computer Architecture, 2016

433 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/bdcafffa64ad0c16bd98dc3b6c627c42c939fa1a

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

In Information Systems

Citations in the corpus

SgxPectre: Stealing Intel Secrets from SGX Enclaves Via Speculative Execution (2018, background): “haretypically effective, but are limited in that the time window required to have major processor vendors to incorporate them in commercialhardwareis verylong. System solutionsonlymodifysystemsoftware[38,73,44,87]. However, these solutions are not directly applicable to SGX enclaves as the system so”
Survey of Attacks and Defenses on Edge-Deployed Neural Networks (2019, background): “aggressive compiler optimizations, cache partitioning [67] or disallowing resource sharing as defenses against cache-based SC.”
Translation Leak-aside Buffer: Defeating Cache Side-channel Protections with TLB Attacks (2018, methodology): “This demonstrates TLBleed can by-pass state-of-art defenses that rely on Intel CAT (or similar mechanisms) [37].”
A survey of microarchitectural timing attacks and countermeasures on contemporary hardware (2016, methodology): “2), CATalyst [108] partitions the LLC into a hybrid hardware and software managed cache.”
Malware Guard Extension: Using SGX to Conceal Cache Attacks (2017, methodology): “[83] proposed a system that uses CAT to protect general purpose software and cryptographic algorithms.”
Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures (2018, methodology): “Another approach is to use cache partitioning, such as Intel CAT (Cache Allocation Technology), which assigns different ways of the LLC to different applications [44].”
ARMageddon: Cache Attacks on Mobile Devices (2015, background): “Cryptographic algorithms can also be protected using cache partitioning [35].”
BranchScope: A New Side-Channel Attack on Directional Branch Predictor (2018, background): “Alternatively, mechanisms to request a private partition of the BPU may be supported [37].”
A Formal Foundation for Secure Remote Execution of Enclaves (2017, background): “Academic work seeking to improve the security of aspects of conventional processors is also abundant [23, 40, 41, 50].”
InvisiSpec: Making Speculative Execution Invisible in the Cache Hierarchy (2018, background): “Other mechanisms, such as Catalyst [44] and StealthMem [45], prevent an attacker from observing a victim’s access patterns on a secure-sensitive region.”
Sanctum: Minimal Hardware Extensions for Strong Software Isolation (2016, methodology): “CATalyst [37] trusts the Xen hypervisor to correctly tame Intel’s Cache Allocation Technology into providing cache pinning, which can only secure software whose code and data fits into a fraction of the LLC.”
SgxPectre Attacks: Leaking Enclave Secrets via Speculative Execution (2018, background): “haretypically effective, but are limited in that the time window required to have major processor vendors to incorporate them in commercialhardwareis verylong. System solutionsonlymodifysystemsoftware[38,73,44,87]. However, these solutions are not directly applicable to SGX enclaves as the system so”