International Association
for Cryptologic Research

Even given a state-of-the-art masking scheme, masked software implementation of some cryptography functionality can pose significant challenges stemming, e.g., from simultaneous requirements for efficiency and security. In this paper we design an Instruction Set Extension (ISE) to address a specific element of said challenge, namely the elimination of leakage stemming from architectural and microarchitectural overwriting. Conceptually, the ISE allows a leakage-focused behavioural hint to be communicated from software to the micro-architecture: using it informs how computation is realised when applied to masking-specific data, which then offers an opportunity to eliminate associated leakage. We develop prototype, latencyand area-optimised implementations of the ISE design based on the RISC-V Ibex core. Using them, we demonstrate that use of the ISE can close the gap between assumptions about and actual behaviour of a device and thereby deliver an improved security guarantee.

In this paper, we describe an extensible experimental infrastructure for evaluating the micro-architectural leakage, based on power consumption, that stems from a physical device. Building on existing literature, we use it to systematically study 14 different devices, which span 4 different instruction set architectures and 4 different vendors. The study allows a characterisation of each device with respect to any leakage effects stemming from sources within the micro-architectural implementation. We use it, for example, to identify and document several novel leakage effects (e.g., due to speculative instruction execution), and scenarios where an assumption about leakage is non-portable between different yet compatible devices.Ours is the widest study of its kind we are aware of, and highlights a range of challenges with respect to 1) the design, implementation, and evaluation of, e.g., masking schemes, 2) construction of accurate leakage models, and 3) selection of suitable devices for experimental research. For example, in relation to 1), we cast further doubt on whether a given device upholds the assumptions required by a given masking scheme; in relation to 2), we conclude that (statistical or formal) device leakage models must include information about the micro-architecture being modelled; in relation to 3), we claim the near mono-culture of devices that dominates existing literature is insufficient to support general claims regarding leakage. This is particularly important in the context of the FIPS 140-3 standard for non-invasive side-channel evaluation.

Leakage simulators offer the tantalising promise of easy and quick testing of software with respect to the presence of side channel leakage. The quality of their build in leakage models is therefore crucial, this includes the faithful inclusion of micro-architectural leakage. Microarchitectural leakage is a reality even on low- to mid-range commercial processors, such as the ARM Cortex M series. Dealing with it seems initially infeasible in a grey box setting: how should we describe it if micro-architectural elements are not publicly known? We demonstrate, for the first time, that it is feasible, using a recent leakage modelling technique, to reverse engineer significant elements of the micro-architectural leakage of a commercial processor. Our approach first recovers the micro-architectural leakage of each stage in the pipeline, and the leakage of elements that are known to produce glitches. Using the reverse engineered leakage features we build an enhanced version of the popular leakage simulator ELMO.

In both hardware and software, masking can represent an effective means of hardening an implementation against side-channel attack vectors such as Differential Power Analysis (DPA). Focusing on software, however, the use of masking can present various challenges: specifically, it often 1) requires significant effort to translate any theoretical security properties into practice, and, even then, 2) imposes a significant overhead in terms of efficiency. To address both challenges, this paper explores the use of an Instruction Set Extension (ISE) to support masking in software-based implementations of a range of (symmetric) cryptographic kernels including AES: we design, implement, and evaluate such an ISE, using RISC-V as the base ISA. Our ISE-supported first-order masked implementation of AES, for example, is an order of magnitude more efficient than a software-only alternative with respect to both execution latency and memory footprint; this renders it comparable to an unmasked implementation using the same metrics, but also first-order secure.

Ge et al. [GYH18] propose the augmented ISA (or aISA), a central tenet of which is the selective exposure of micro-architectural resources via a less opaque abstraction than normal. The aISA proposal is motivated by the need for control over such resources, for example to implement robust countermeasures against microarchitectural attacks. In this paper, we apply an aISA-style approach to challenges stemming from analogue micro-architectural leakage; examples include power-based Hamming weight and distance leakage from relatively fine-grained resources (e.g., pipeline registers), which are not exposed in, and so cannot be reliably controlled via, a normal ISA. Specifically, we design, implement, and evaluate an ISE named FENL: the ISE acts as a fence for leakage, preventing interaction between, and hence leakage from, instructions before and after it in program order. We demonstrate that the implementation and use of FENL has relatively low overhead, and represents an effective tool for systematically localising and reducing leakage.

Secure, efficient execution of AES is an essential requirement on most computing platforms. Dedicated Instruction Set Extensions (ISEs) are often included for this purpose. RISC-V is a (relatively) new ISA that lacks such a standardized ISE. We survey the state-of-the-art industrial and academic ISEs for AES, implement and evaluate five different ISEs, one of which is novel. We recommend separate ISEs for 32 and 64-bit base architectures, with measured performance improvements for an AES-128 block encryption of 4x and 10x with a hardware cost of 1.1K and 8.2K gates respectively, when compared to a software-only implementation based on use of T-tables. We also explore how the proposed standard bit-manipulation extension to RISC-V can be harnessed for efficient implementation of AES-GCM. Our work supports the ongoing RISC-V cryptography extension standardisation process.

Masking is a well loved and widely deployed countermeasure against side channel attacks, in particular in software. Under certain assumptions (w.r.t. independence and noise level), masking provably prevents attacks up to a certain security order and leads to a predictable increase in the number of required leakages for successful attacks beyond this order. The noise level in typical processors where software masking is used may not be very high, thus low masking orders are not sufficient for real world security. Higher order masking however comes at a great cost, and therefore a number techniques have been published over the years that make such implementations more efficient via parallelisation in the form of bit or share slicing. We take two highly regarded schemes (ISW and Barthe et al.), and some corresponding open source implementations that make use of share slicing, and discuss their true security on an ARM Cortex-M0 and an ARM Cortex-M3 processor (both from the LPC series). We show that micro-architectural features of the M0 and M3 undermine the independence assumptions made in masking proofs and thus their theoretical guarantees do not translate into practice (even worse it seems unpredictable at which order leaks can be expected). Our results demonstrate how difficult it is to link theoretical security proofs to practical real-world security guarantees.

DOI: 10.13154/tches.v2018.i1.I-IV

CAESAR has caused a heated discussion regarding the merits of one-pass encryption and online ciphers. The latter is a keyed, length preserving function which outputs ciphertext blocks as soon as the respective plaintext block is available as input. The immediacy of an online cipher affords a clear performance advantage, but it comes at a price: ciphertext blocks cannot depend on later plaintext blocks, limiting diffusion and hence security. We show how one can attain the best of both worlds by providing provably secure constructions, achieving full cipher security, based on applications of an online cipher around blockwise reordering layers. Explicitly, we show that with just two calls to the online cipher, prp security up to the birthday bound is both attainable and maximal. Moreover, we demonstrate that three calls to the online cipher suffice to obtain beyond birthday bound security. We provide a full proof of this for a prp construction, and, in the ±prp setting, security against adversaries who make queries of any single length. As part of our investigation, we extend an observation by Rogaway and Zhang by further highlighting the close relationship between online ciphers and tweakable blockciphers with variable-length tweaks.