The article is devoted to software bitsliced implementation of randomly generated$8\times 8$S-Box block ciphers, focused on the use of logical SIMD instructions from the SSE, AVX and AVX-512 extensions in ×86-64 processors. A heuristic algorithm for minimizing non-algebraic S-Boxes in three logical bases is proposed: universal—based on logical instructions AND, OR, XOR, NOT, which allows implementation on any 8/16/32/ 64-bit processors; extended—based on the instructions AND, OR, XOR, NOT, AND-NOT, which allows implementation on ×86-64 processors; ternary—based on ternary logic instructions, for implementation on ×86-64 processors with AVX-512 support. On average, bitsliced representations of non-algebraic S-Boxes in these logical bases require 400/380/200 logical instructions, respectively. The performance of bitsliced implementations of the S-Box cipher “Kalyna” using logical instructions SSE/AVX/ AVX-512 for the Intel Xeon Skylake-SP processor was measured. A fast alternative—non-bitsliced approach to the bytesliced SubBytes operation based on the AVX-512VBMI extension, resistant to timing and cache attacks—is proposed.

This article describes the implementation of the AES-GCM for IoT-oriented low-end 8/16/32-bit general-purpose processors. Although various aspects of implementations of the AES-GCM for high-end processors and hardware were examined in detail, the low-end processors to a lesser extent. This article estimates the speed and memory demand for various approaches to ensuring resistance to attacks, such as timing analysis and simple power analysis by ensuring the constant algorithm execution time. A particular attention is paid to the low-level multiplication implementation in GF (2128) for each architecture as a key galois/counter mode operation, because low-end processors do not have ready-made instructions for carry-less multiplication. For each AVR/MSP430/ARM Cortex-M3 processor core, a constant time implementation of carry-less multiplication is proposed, the performance of which approaches the Not Constant Time algorithm.

In this paper the authors introduced a concept of a standalone device able to recognize some of the emotions of people walking towards a robot, before they even approach it. The early emotion recognition is being used for preparation and recompilation of the robot's conversation tree in order to limit the number of possible phrases by excluding the least judicious ones. An overall system concept was presented, as well as a description of a proof-of-concept practical implementation. Exemplary libraries were installed and executed within an Embedded System, the most useful implementation was described in more detail.