Linear cryptanalysis against block ciphered system under noisy ciphertexts

In this paper, we study the effect of channel errors on the performance of linear cryptanalysis against block ciphered system. We study DES block cipher working in cipher feedback mode (CFB) as a special case. In our model, eavesdropper launches linear attack by querying an oracle which provides her with corrupted ciphertexts over a binary symmetric channel (BSC). A new verification strategy in linear attack has been designed and numerically optimized to allow Eve to mount a successful attack in noisy environments. However, we show that even by utilizing this optimized strategy, there is still possibility of misdetection in Eve's cryptanalysis, which directly depends on the channel degradation level. Numerical results show that the proposed attack strategy lets Eve maintain a high performance even for relatively high noise levels. On the other hand, they suggest that due to Eve's possible failures in her attack, tunable cross over probability of the channel can bring about the lowest performance for Eve as well as a higher security.