18 research outputs found
A survey on machine learning applied to symmetric cryptanalysis
No full textIn this work we give a short review of the recent progresses of machine learning techniques applied to cryptanalysis of symmetric ciphers, with particular focus on artificial neural networks. We start with some terminology and basics of neural networks, to then classify the recent works in two categories: "black-box cryptanalysis", techniques that not require previous information about the cipher, and "neuro-aided cryptanalysis", techniques used to improve existing methods in cryptanalysis
Milwaukee Semi-centennial march
No full textMILWAUKEE SEMI-CENTENNIAL MARCH
Milwaukee Semi-centennial march ([1])
Titelseite ([1])
Noten ([2]
A Cipher-Agnostic Neural Training Pipeline with Automated Finding of Good Input Differences
No full textNeural cryptanalysis is the study of cryptographic primitives through machine learning techniques. Following Gohr’s seminal paper at CRYPTO 2019, a focus has been placed on improving the accuracy of such distinguishers against specific primitives, using dedicated training schemes, in order to obtain better key recovery attacks based on machine learning. These distinguishers are highly specialized and not trivially applicable to other primitives. In this paper, we focus on the opposite problem: building a generic pipeline for neural cryptanalysis. Our tool is composed of two parts. The first part is an evolutionary algorithm for the search of good input differences for neural distinguishers. The second part is DBitNet, a neural distinguisher architecture agnostic to the structure of the cipher. We show that this fully automated pipeline is competitive with a highly specialized approach, in particular for SPECK32, and SIMON32. We provide new neural distinguishers for several primitives (XTEA, LEA, HIGHT, SIMON128, SPECK128) and improve over the state-of-the-art for PRESENT, KATAN, TEA and GIMLI
How to Securely Implement Cryptography in Deep Neural Networks
No full textThe wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g, to decrypt an encrypted input, to verify that this input is authorized, or to hide a secure watermark in the output). The problem is that cryptographic primitives are typically designed to run on digital computers that use Boolean gates to map sequences of bits to sequences of bits, whereas DNNs are a special type of analog computer that uses linear mappings and ReLUs to map vectors of real numbers to vectors of real numbers. This discrepancy between the discrete and continuous computational models raises the question of what is the best way to implement standard cryptographic primitives as DNNs, and whether DNN implementations of secure cryptosystems remain secure in the new setting, in which an attacker can ask the DNN to process a message whose bits are arbitrary real numbers.
In this paper we lay the foundations of this new theory, defining the meaning of correctness and security for implementations of cryptographic primitives as ReLU-based DNNs. We then show that the natural implementations of block ciphers as DNNs can be broken in linear time by using such nonstandard inputs. We tested our attack in the case of full round AES-128, and had success rate in finding randomly chosen keys. Finally, we develop a new method for implementing any desired cryptographic functionality as a standard ReLU-based DNN in a provably secure and correct way. Our protective technique has very low overhead (a constant number of additional layers and a linear number of additional neurons), and is completely practical
A Cipher-Agnostic Neural Training Pipeline with Automated Finding of Good Input Differences
No full textNeural cryptanalysis is the study of cryptographic primitives throughmachine learning techniques. Following Gohr’s seminal paper at CRYPTO 2019, afocus has been placed on improving the accuracy of such distinguishers against specific primitives, using dedicated training schemes, in order to obtain better key recovery attacks based on machine learning. These distinguishers are highly specialized and not trivially applicable to other primitives. In this paper, we focus on the opposite problem: building a generic pipeline for neural cryptanalysis. Our tool is composed of two parts. The first part is an evolutionary algorithm for the search of good input differences for neural distinguishers. The second part is DBitNet, a neuraldistinguisher architecture agnostic to the structure of the cipher. We show thatthis fully automated pipeline is competitive with a highly specialized approach, inparticular for SPECK32, and SIMON32. We provide new neural distinguishers forseveral primitives (XTEA, LEA, HIGHT, SIMON128, SPECK128) and improve overthe state-of-the-art for PRESENT, KATAN, TEA and GIMLI
Survey: 6 Years of Neural Differential Cryptanalysis
No full textAt CRYPTO 2019, A. Gohr introduced Neural Differential Cryptanalysis and used deep learning to improve the state-of-the-art cryptanalysis of 11-round SPECK32. As of February 2025, according to Google Scholar, Gohr’s article has been cited 229 times. The variety of targeted cryptographic primitives, techniques, settings, and evaluation methodologies that appear in these follow-up works grants a careful survey, which we provide in this paper. More specifically, we propose a taxonomy of these 229 publications and systematically review the 66 papers focusing on neural differential distinguishers, pointing out promising directions. We then highlight future challenges in the field, particularly the need for improved comparability of neural distinguishers and advancements in scaling. This survey helps researchers and engineers to identify the leading neural differential attacks, compare their performance, and highlight the outstanding open problems in AI-assisted cryptanalysis
Generic Partial Decryption as Feature Engineering for Neural Distinguishers
No full textIn Neural Cryptanalysis, a deep neural network is trained as a cryptographic distinguisher between pairs of ciphertexts , where is either a random permutation or a block cipher, is a fixed difference. The AutoND framework aims to se neural distinguishers that are treated as a generic tool and discourages cipher-specific optimizations. On the other hand, works such as obtain superior distinguishers by adding dedicated features, such as selected parts of the difference in the previous rounds, to the input of the neural distinguishers. In this paper, we study as a feature engineering technique and integrate it within a fully automated pipeline, where we evaluate its effect independently of the number of pairs per sample, with which feature engineering is often combined. We show that this technique matches state-of-the-art dedicated approaches on Simon and Simeck. Additionally, we apply it to Aradi, and present a practical neural-assisted key recovery for 5 rounds, as well as a 7-rounds key recovery with time complexity. Additionally, we derive useful information from the neural distinguishers and propose a non-neural version of our 5-round key recovery
Workload-Balanced Pruning for Sparse Spiking Neural Networks
No full textPruning for Spiking Neural Networks (SNNs) has emerged as a fundamental
methodology for deploying deep SNNs on resource-constrained edge devices.
Though the existing pruning methods can provide extremely high weight sparsity
for deep SNNs, the high weight sparsity brings a workload imbalance problem.
Specifically, the workload imbalance happens when a different number of
non-zero weights are assigned to hardware units running in parallel. This
results in low hardware utilization and thus imposes longer latency and higher
energy costs. In preliminary experiments, we show that sparse SNNs (~98% weight
sparsity) can suffer as low as ~59% utilization. To alleviate the workload
imbalance problem, we propose u-Ticket, where we monitor and adjust the weight
connections of the SNN during Lottery Ticket Hypothesis (LTH) based pruning,
thus guaranteeing the final ticket gets optimal utilization when deployed onto
the hardware. Experiments indicate that our u-Ticket can guarantee up to 100%
hardware utilization, thus reducing up to 76.9% latency and 63.8% energy cost
compared to the non-utilization-aware LTH method.Comment: 11 pages. Accepted to IEEE Transactions on Emerging Topics in
Computational Intelligence (2024
