Matthias Probst

Manuel Brosch, Matthias Probst, Stefan Kögler et al.

The use of neural networks in edge devices is increasing, which introduces new security challenges related to the neural networks' confidentiality. As edge devices often offer physical access, attacks targeting the hardware, such as side-channel analysis, must be considered. To enhance the performance of neural network inference, hardware accelerators are commonly employed. This work investigates the influence of parallel processing within such accelerators on correlation-based side-channel attacks that exploit power consumption. The focus is on neurons that are part of the same fully-connected layer, which run parallel and simultaneously process the same input value. The theoretical impact of concurrent multiply-and-accumulate operations on overall power consumption is evaluated, as well as the success rate of correlation power analysis. Based on the observed behavior, equations are derived that describe how the correlation decreases with increasing levels of parallelism. The applicability of these equations is validated using a vector-multiplication unit implemented on an FPGA.

Elie Bursztein, Michael Gruber, Karel Král et al.

Side Channel Analysis (SCA) relaxes the black-box assumption of conventional cryptanalysis by incorporating physical measurements acquired during cryptographic operations. Electro-magnetic (EM) emissions of a chip during computations often provide a very valuable source of side channel leakage. During the evaluation of a chip for electro-magnetic side channel emissions one needs to position an electro-magnetic probe in an advantageous position relative to the chip. Previous literature focused on hot-spot finding and to a lower extend repositioning. Trace augmentations have been considered to aid portability of profiling using one physical device and attacking another device. This paper focuses on training a single neural network using traces from multiple EM probe positions to detect leakage from a larger area over the attacked device. We provide dual evaluation of EM traces - from two completely independent labs - profiling on data from one lab and attacking traces from the other lab.

Michael Gruber, Matthias Probst, Michael Tempelmeier

Ineffective Fault Analysis (SIFA) was introduced as a new approach to attack block ciphers at CHES 2018. Since then, they have been proven to be a powerful class of attacks, with an easy to achieve fault model. One of the main benefits of SIFA is to overcome detection-based and infection-based countermeasures. In this paper we explain how the principles of SIFA can be applied to GIMLI, an authenticated encryption cipher participating the NIST-LWC competition. We identified two possible rounds during the intialization phase of GIMLI to mount our attack. If we attack the first location we are able to recover 3 bits of the key uniquely and the parity of 8 key-bits organized in 3 sums using 180 ineffective faults per biased single intermediate bit. If we attack the second location we are able to recover 15 bits of the key uniquely and the parity of 22 key-bits organized in 7 sums using 340 ineffective faults per biased intermediate bit. Furthermore, we investigated the influence of the fault model on the rate of ineffective faults in GIMLI. Finally, we verify the efficiency of our attacks by means of simulation.