Side-channel vulnerability factor: A metric for measuring information leakage

Abstract

There have been many attacks that exploit side-effects of program execution to expose secret information and many proposed countermeasures to protect against these attacks. However there is currently no systematic, holistic methodology for understanding information leakage. As a result, it is not well known how design decisions affect information leakage or the vulnerability of systems to side-channel attacks.In this paper, we propose a metric for measuring information leakage called the Side-channel Vulnerability Factor (SVF). SVF is based on our observation that all sidechannel attacks ranging from physical to microarchitectural to software rely on recognizing leaked execution patterns. SVF quantifies patterns in attackers' observations and measures their correlation to the victim's actual execution patterns and in doing so captures systems' vulnerability to side-channel attacks.In a detailed case study of on-chip memory systems, SVF measurements help expose unexpected vulnerabilities in whole-system designs and shows how designers can make performance-security trade-offs. Thus, SVF provides a quantitative approach to secure computer architecture.

Cache-Oblivious and Data-Oblivious Sorting and Applications

“…In particular, existing schemes no longer retain security if the adversary can additionally observe which cache-lines are accessed within the cache (i.e., when no cache miss occurs). In other words, known external-memory oblivious algorithms [33,32,35] are vulnerable to a well-known cache-timing attack [53,21,68,67] that arises due to the timesharing of on-chip caches among multiple processes. Specifically, an adversary who controls a piece of software co-resident on the same machine as the victim application, can selectively evict the victim application's cache-lines and thus infer which cachelines the victim application is requesting through careful timing measurements.…”

“…Since the mainstream commodity processors (even secure processors such as Intel's SGX) allow multiple processes or multiple virtual machines to time-share the same on-chip cache, a well-known cache-timing attack is possible where a malicious process (or virtual machine respectively) co-resides on the same physical machine as the victim process (or virtual machine respectively) can learn the victim process's internal secrets such as decryption keys [53,21,68,67]. In such a cache-timing attack, the attacker process selectively evicts a subset of the victim process's cache-lines from the shared cache.…”

TimeWarp: Rethinking timekeeping and performance monitoring mechanisms to mitigate side-channel attacks

“…7. For the results presented in this appendix, we used the same set of simulations as detailed in the original SVF paper [5], though we only use the "in order" attackers on SMT-enabled systems with the Timewarp microarchitectural protection.…”

“…As in the SVF paper [5], we present results in the form of a cumulative histogram, allowing us to quickly look at many configurations 3 . In Figure 7 we examine SMT systems at a fine granularity of 10,000 victim instructions.…”

“…To review, SVF measures the leakage of execution patterns through a system under specific assumptions about the attacker and victim [5]. We mea-…”