On the resistance of new lightweight block ciphers against differential cryptanalysis

Abstract

Many recently proposed lightweight block ciphers lack security evaluation against generic cryptanalytic attacks such as differential cryptanalysis. In this paper, we contribute towards security evaluation efforts by investigating four lightweight Feistel-based block ciphers including SLIM, LBC-IoT, SCENERY, and LCB. SLIM claims resistance to differential cryptanalysis since, using a heuristic technique, its designers could only find a 7-round differential trail. Despite having no analysis of security against attacks such as differential cryptanalysis, the designers of LBC-IoT and LCB claimed that their ciphers are secure. Meanwhile, the designers of SCENERY claim that the best 11-round differential trail for the cipher has a probability of 2−66. To substantiate these claims, we propose attacks on all four ciphers based on differential cryptanalysis. We presented practical key recovery attacks on SLIM which can retrieve the final round key for up to 14 rounds with a time complexity of 232. LBC-IoT was found to be weaker against differential cryptanalysis despite sharing many similarities with SLIM, whereby a key recovery attack of up to 19 rounds is possible with time complexity 231. For SCENERY, we found a differential trail of up to 12 rounds with probability 2−60, which was used as the distinguisher for a 13-round key recovery attack. We also discovered that LCB's design lacks nonlinearity, allowing us to easily derive deterministic differential trails regardless of the number of rounds. This flaw allowed us to perform a trivial distinguishing attack using a single known ciphertext. By using a different S-box to address this flaw, LCB is now more resilient to differential cryptanalysis than SLIM and LBC-IoT when using the same number of rounds. Our paper presents new independent cryptanalysis results for these ciphers.