International audience

This paper introduces a novel sensor that is capable of detecting faults injected by electromagnetic disturbances. The sensor has been designed from an understanding of the physical mechanisms of ElectroMagnetic Fault Injection (EMFI). A recent study has identified an EMFI mechanism based on the timing violation fault model, which highlights the coexistence of two distinct mechanisms: electromagnetic disturbances that are coupled to the target’s power distribution network, which can cause timing faults by extending the propagation time of logic gates beyond the clock period, and disturbances that are coupled to the target’s clock distribution network, which can cause timing constraint violations due to EMFI-induced voltage glitches within the target’s clock tree. Building on this work, we have investigated the mechanism of EMFI-induced clock glitches, providing useful insights for designing a new sensor. The sensor incorporates two dummy clock paths that are maintained in a frozen state within the circuit. Both paths are respectively capable of detecting both positive and negative EMFI-induced glitches along these paths. The proposed sensor offers significant advantages, including full digitization, ease of implementation, low cost in terms of silicon area, low power consumption, and a high fault detection rate. Accurate design and experimental tests were performed on an FPGA board. Validation experiments were supported by spatial and temporal sensitivity maps covering the full-frequency spectrum of the target, which confirmed the effectiveness of the sensor.

Fault injection attacks can be carried out against an operating circuit by exposing it to EM perturbations. These attacks can be detected using embedded digital sensors based on the EM fault injection mechanism, as the one introduced by El Baze et al. [1] which uses the sampling fault model [2], [3]. We tested on an experimental basis the efficiency of this sensor embedded in the AES accelerator of an FPGA. It proved effective when the target was clocked at moderate frequency (the injected faults were consistent with the sampling fault model). As the clock frequency was progressively increased, faults started to escape detection, which raises warnings about possible limitations of the sampling model. Further tests at frequencies close to the target maximal frequency revealed faults injected according to a timing fault model. Both series of experimental results ascertain that EM injection can follow at least two different fault models. Undetected faults and the existence of different fault injection mechanisms cast doubt upon the use of sensors based on a single model.

Investigating the dynamics and mechanisms of Electromagnetic Fault Injection (EMFI) attacks, which expose an active circuit to electromagnetic disturbances, presents a persisting challenge due to the diverse and complex fault mechanisms involved. An improved understanding of EMFI modeling is paramount for developing proficient on-chip detection sensors, serving as countermeasures to these attacks. In light of this, our research evaluated the effectiveness of EMFI detection sensors, introduced by Elbaze et al., which rest on the premise that the sampling fault model accounts for EMFI. To assess the functionality of these sensors, we integrated them into an Advanced Encryption Standard (AES) accelerator of a Field-Programmable Gate Array (FPGA) and performed a series of experiments. The resulting evidence suggests that the explanation for EMFI is not a singular fault model but rather, two underlying mechanisms are implicated. At high frequencies, which corresponds to low slack, electromagnetic disturbances, in tandem with the target's Power Distribution Network (PDN), initiated timing constraint violations. This violation subsequently increased the logic propagation times, surpassing the clock period. Contrarily, at low to moderate frequencies, the induced faults generally aligned with the sampling fault model. However, certain deviations from the theoretical framework called into question the model's validity. Upon a deeper examination of the results, we determined that these faults, rather than being sampling faults, were tied to a different mechanism. Electromagnetic disturbances, when coupled with a target's Clock Distribution Network (CDN), can cause timing constraint violations due to EMFI-induced voltage glitches within the target's clock tree. By integrating the mechanisms of EMFI-induced clock glitches and timing faults into the timing violations fault model, we attain a holistic comprehension of EMFI mechanisms. It encapsulates both mechanisms induced by EMFI, spanning the full-frequency spectrum of the target.

Detecting hardware trojans is a difficult task in general. In this article we study hardware trojan horses insertion and detection in cryptographic intellectual property (IP) blocks. The context is that of a fabless design house that sells IP blocks as GDSII hard macros, and wants to check that final products have not been infected by trojans during the foundry stage. First, we show the efficiency of a medium cost hardware trojans detection method if the placement or the routing have been redone by the foundry. It consists in the comparison between optical microscopic pictures of the silicon product and the original view from a GDSII layout database reader. Second, we analyze the ability of an attacker to introduce a hardware trojan horse without changing neither the placement nor the routing of the cryptographic IP logic. On the example of an AES engine, we show that if the placement density is beyond 80%, the insertion is basically impossible. Therefore, this settles a simple design guidance to avoid trojan horses insertion in cryptographic IP blocks: have the design be compact enough, so that any functionally discreet trojan necessarily requires a complete replace and re-route, which is detected by mere optical imaging (and not complete chip reverse-engineering).

In this paper we put forward a high-performance biometric fingerprint authentication algorithm for Match-On-Card (MOC) applications, compatible with the INCITS 378 and ISO/IEC 19794 standard. An efficient hardware implementation is proposed to adapt the algorithm for constrained embedded systems as smart cards. Time and memory complexities are reduced such that both integration and real time matching-on card can be met. The proposed architecture drops the required memory to 0.05% w.r.t. initial complexity, without any performance degradation. Therefore, the proposed solution is sufficient to meet the high level of security and the low computation time required in demanding authentication systems (e.g airports, electronic commerce and banking transactions).

Electromagnetic analysis is an important class of attacks against cryptographic devices. In this article, we prove that Correlation-based on ElectroMagnetic Analysis (CEMA) on a hardware-based high-performance AES module is possible from a distance as far as 50 cm. First we show that the signal-to-noise ratio (SNR) tends to a non-zero limit when moving the antenna away from the cryptographic device. An analysis of the leakage structure shows that the Hamming distance model, although suitable for small distances gets more and more distorted when the antenna is displaced far from the device. As we cannot devise any physical model that would predict the observations, we instead pre-characterized it using a first order templates construction. With this model, we enhanced the CEMA by a factor up to ten. Therefore, we conclude that EMA at large distance is feasible with our amplification strategy coupled to an innovative training phase aiming at precharacterizing accurate coefficients of a parametric weighted distance leakage model.

Fault injections constitute a major threat to the security of embedded systems. Errors occurring in the cryptographic algorithms have been shown to be extremely dangerous, since powerful attacks can exploit few of them to recover the full secrets. Most of the resistance techniques to perturbation attacks have relied so far on the detection of faults. We present in this paper another strategy, based on the resilience against fault attacks. The core idea is to allow an erroneous result to be outputted, but with the assurance that this faulty information conveys no information about the secrets concealed in the chip. We first underline the benefits of FIR: false positive are never raised, secrets are not erased uselessly in case of uncompromising faults injections, which increases the card lifespan if the fault is natural and not malevolent, and FIR enables a high potential of resistance even in the context of multiple faults. Then we illustrate two families of fault injection resilience (FIR) schemes suitable for symmetric encryption. The first family is a protocol-level scheme that can be formally proved resilient. The second family mobilizes a special logic-level architecture of the cryptographic module. We notably detail how a countermeasure of this later family, namely dual-rail with precharge logic style, can both protect both against active and passive attacks, thereby bringing a combined global protection of the device. The cost of this logic is evaluated as lower than detection schemes. Finally, we also give some ideas about the modalities of adjunction of FIR to some certification schemes.

Cryptographic circuits are nowadays subject to attacks that no longer focus on the algorithm but rather on its physical implementation. Attacks exploiting information leaked by the hardware implementation are called side-channel attacks (SCAs). Among these attacks, the differential power analysis (DPA) established by Paul Kocher et al. in 1998 represents a serious threat for CMOS VLSI implementations. Different countermeasures that aim at reducing the information leaked by the power consumption have been published. Some of these countermeasures use sophisticated back-end-level constraints to increase their strength. As suggested by some preliminary works (e.g., by Li from Cambridge University), the prediction of the actual security level of such countermeasures remains an open research area. This paper tackles this issue on the example of the AES SubBytes primitive. Thirteen implementations of SubBytes, in unprotected, WDDL, and SecLib logic styles with various back-end-level arrangements are studied. Based on simulation and experimental results, we observe that static evaluations on extracted netlists are not relevant to classify variants of a countermeasure. Instead, we conclude that the fine-grained timing behavior is the main reason for security weaknesses. In this respect, we prove that SecLib, immune to early-evaluation problems, is much more resistant against DPA than WDDL.

In this paper, we propose a preprocessing method to improve side channel attacks (SCAs) on dual-rail with precharge logic (DPL) countermeasure family. The strength of our method is that it uses intrinsic characteristics of the countermeasure: classical methods fail when the countermeasure is perfect, whereas our method still works and enables us to perform advanced attacks. We have experimentally validated the proposed method by attacking a DES cryptoprocessor embedded in a field programmable gates array (FPGA), and protected by the wave dynamic differential logic (WDDL) countermeasure. This successful attack, unambiguous as the full key is retrieved, is the first to be reported.

Since the first announcement of a Side Channel Analysis (SCA) about ten years ago, considerable research has been devoted to studying these attacks on Application Specific Integrated Circuits (ASICs), such as smart cards or TPMs. In this article, we compare power-line attacks with ElectroMagnetic (EM) attacks, specifically targeting Field Programmable Gate Array devices (FPGAs), as they are becoming widely used for sensitive applications involving cryptography. We show experimentally that ElectroMagnetic Analysis (EMA) is always faster than the historical Differential Power Analysis (DPA) in retrieving keys of symmetric ciphers. In addition, these analyses prove to be very convenient to conduct, as they are totally non-invasive. Research reports indicate that EMA can be conducted globally, typically with macroscopic home-made coils circling the device under attack, with fair results. However, as accurate professional EM antennas are now becoming more accessible, it has become commonplace to carry out EM analyses locally. Cartography has been carried out by optical means on circuits realized with technology greater than 250 nanometers. Nonetheless, for deep submicron technologies, the feature size of devices that are spied upon is too small to be visible with photographic techniques. In addition, the presence of the 6+ metallization layers obviously prevents a direct observation of the layout. Therefore, EM imaging is emerging as a relevant means to discover the underlying device structure. In this article, we present the first images of deep-submicron FPGAs. The resolution is not as accurate as photographic pictures: we notably compare the layout of toy design examples placed at the four corners of the FPGAs with the EM images we collected. We observe that EM imaging has the advantage of revealing active regions, which can be useful in locating a particular processor (visible while active---invisible when inactive). In the context of EM attacks, we stress that the exact localization of the cryptographic target is not necessary: the coarse resolution we obtain is sufficient. We note that the EM imaging does not reveal the exact layout of the FPGA, but instead directly guides the attacker towards the areas which are leaking the most. We achieve attacks with an accurate sensor, both far from (namely on a SMC capacitor on the board) and close to (namely directly over the FPGA) the encryption co-processor. As compared to the previously published attacks, we report a successful attack on a DES module in fewer than 6,300 measurements, which is currently the best cracking performance against this encryption algorithm implemented in FPGAs.

This article presents a family of cryptographic ASICs, called SecMat, designed in CMOS 130 nanometer technology by the authors with the help of STMicroelectronics.The purpose of these prototype circuits is to experience with the published ``implementation-level'' attacks(SPA, DPA, EMA, templates, DFA). We report our conclusions about the practicability of these attacks:which ones are the most simple to mount, and which ones require more skill, time, equipments, etc.The potential of FPGAs as security evaluation commodities at design time is also detailed.Then, we discuss about ``dual counter-measures'', that are meant to resist both passive and active attacks.This study started four years ago with TIMA (Grenoble), in the framework of the project MARS. We highlight some research directions towards dependable and cost-effective dual counter-measures.

Field programmable gate arrays (FPGAs) become very popular for embedded cryptographic operations. In order to resist side-channel attacks, FPGAs must implement reasoned countermeasures. The most efficient way to mitigate attacks is to adopt a gate-level protection. Two secure gates families exist: those that ldquohiderdquo and those that ldquomaskrdquo side-channel leakage. In this article, we detail methods to reduce the size of wave dynamic differential logic (WDDL) implementations. These circuits are designed to hide any physical leak by ensuring a data-independent activity. This study is meant to be generic, and thus applies to any 4 rarr 1 LUT-based FPGAs. Further optimizations can be reached by taking advantage of some FPGAs proprietary features. Our solutions include RTL code modification, synthesizer usage (potentially in a re-entrant way), and ad hoc mapping. We show that linear parts of algorithms can be delegated to a synthesizer, but that non-linear parts are better off to be handled with heuristics. We present a 23 % area gain over the state-of-the-art as for the positive WDDL triple-DES symmetric encryption algorithm.

Logic styles with constant power consumption are promising solutions to counteract side-channel attacks on sensitive cryptographic devices. Recently, one vulnerability has been identified in a standard-cell-based power-constant logic called WDDL. Another logic, nicknamed SecLib, is considered and does not present the flaw of WDDL. In this paper, we evaluate the security level of WDDL and SecLib. The methodology consists in embedding in a dedicated circuit one unprotected DES coprocessor along with two others, implemented in WDDL and in SecLib. One essential part of this paper is to describe the conception of the cryptographic ASIC, devised to foster side-channel cryptanalyses, in a view to model the strongest possible attacker. The same analyses are carried out successively on the three DES modules. We conclude that, provided that the back-end of the WDDL module is carefully designed, its vulnerability cannot be exploited by the state-of-the-art attacks. Similarly, the SecLib DES module resists all assaults. However, using a principal component analysis, we show that WDDL is more vulnerable than SecLib. The statistical dispersion of WDDL, which reflects the correlation between the secrets and the power dissipation, is proved to be an order of magnitude higher than that of SecLib.