Cybersecurity最新文献

The elliptic curve discrete logarithm problem (ECDLP) is a popular choice for cryptosystems due to its high level of security. However, with the advent of the extended Shor’s algorithm, there is concern that ECDLP may soon be vulnerable. While the algorithm does offer hope in solving ECDLP, it is still uncertain whether it can pose a real threat in practice. From the perspective of the quantum circuits of the algorithm, this paper analyzes the feasibility of cracking ECDLP using an ion trap quantum computer with improved quantum circuits for the extended Shor’s algorithm. We give precise quantum circuits for extended Shor’s algorithm to calculate discrete logarithms on elliptic curves over prime fields, including modular subtraction, three different modular multiplication, and modular inverse. Additionally, we incorporate and improve upon windowed arithmetic in the circuits to reduce the CNOT-counts. Whereas previous studies mostly focused on minimizing the number of qubits or the depth of the circuit, we focus on minimizing the number of CNOT gates in the circuit, which greatly affects the running time of the algorithm on an ion trap quantum computer. Specifically, we begin by presenting implementations of basic arithmetic operations with the lowest known CNOT-counts, along with improved constructions for modular inverse, point addition, and windowed arithmetic. Next, we precisely estimate that, to execute the extended Shor’s algorithm with the improved circuits to factor an n-bit integer, the CNOT-count required is (1237n^3/log n+2n^2+n). Finally, we analyze the running time and feasibility of the extended Shor’s algorithm on an ion trap quantum computer.

In recent years, deep learning (DL) models have achieved significant progress in many domains, such as autonomous driving, facial recognition, and speech recognition. However, the vulnerability of deep learning models to adversarial attacks has raised serious concerns in the community because of their insufficient robustness and generalization. Also, transferable attacks have become a prominent method for black-box attacks. In this work, we explore the potential factors that impact adversarial examples (AEs) transferability in DL-based speech recognition. We also discuss the vulnerability of different DL systems and the irregular nature of decision boundaries. Our results show a remarkable difference in the transferability of AEs between speech and images, with the data relevance being low in images but opposite in speech recognition. Motivated by dropout-based ensemble approaches, we propose random gradient ensembles and dynamic gradient-weighted ensembles, and we evaluate the impact of ensembles on the transferability of AEs. The results show that the AEs created by both approaches are valid for transfer to the black box API.

Federated Learning (FL) suffers from the Non-IID problem in practice, which poses a challenge for efficient and accurate model training. To address this challenge, prior research has introduced clustered FL (CFL), which involves clustering clients and training them separately. Despite its potential benefits, CFL can be computationally and communicationally expensive when the data distribution is unknown beforehand. This is because CFL involves the entire neural networks of involved clients in computing the clusters during training, which can become increasingly time-consuming with large-sized models. To tackle this issue, this paper proposes an efficient CFL approach called LayerCFL that employs a Layer-wised clustering technique. In LayerCFL, clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental methods. Our experimental results demonstrate the effectiveness of LayerCFL in mitigating the impact of Non-IID data, improving the accuracy of clustering, and enhancing computational efficiency.

Abstract

Intrusion detection systems have been proposed for the detection of botnet attacks. Various types of centralized or distributed cloud-based machine learning and deep learning models have been suggested. However, the emergence of the Internet of Things (IoT) has brought about a huge increase in connected devices, necessitating a different approach. In this paper, we propose to perform detection on IoT-edge devices. The suggested architecture includes an anomaly intrusion detection system in the application layer of IoT-edge devices, arranged in software-defined networks. IoT-edge devices request information from the software-defined networks controller about their own behaviour in the network. This behaviour is represented by communication graphs and is novel for IoT networks. This representation better characterizes the behaviour of the device than the traditional analysis of network traffic, with a lower volume of information. Botnet attack scenarios are simulated with the IoT-23 dataset. Experimental results show that attacks are detected with high accuracy using a deep learning model with low device memory requirements and significant storage reduction for training.

Graphical abstract

In today’s interconnected world, network traffic is replete with adversarial attacks. As technology evolves, these attacks are also becoming increasingly sophisticated, making them even harder to detect. Fortunately, artificial intelligence (AI) and, specifically machine learning (ML), have shown great success in fast and accurate detection, classification, and even analysis of such threats. Accordingly, there is a growing body of literature addressing how subfields of AI/ML (e.g., natural language processing (NLP)) are getting leveraged to accurately detect evasive malicious patterns in network traffic. In this paper, we delve into the current advancements in ML-based network traffic classification using image visualization. Through a rigorous experimental methodology, we first explore the process of network traffic to image conversion. Subsequently, we investigate how machine learning techniques can effectively leverage image visualization to accurately classify evasive malicious traces within network traffic. Through the utilization of production-level tools and utilities in realistic experiments, our proposed solution achieves an impressive accuracy rate of 99.48% in detecting fileless malware, which is widely regarded as one of the most elusive classes of malicious software.

The computational complexity of privacy information retrieval protocols is often linearly related to database size. When the database size is large, the efficiency of privacy information retrieval protocols is relatively low. This paper designs an effective privacy information retrieval model based on hybrid fully homomorphic encryption. The assignment method is cleverly used to replace a large number of homomorphic encryption operations. At the same time, the multiplicative homomorphic encryption scheme is first used to deal with the large-scale serialization in the search, and then the fully homomorphic encryption scheme is used to deal with the remaining simple operations. The depth of operations supported by the fully homomorphic scheme no longer depends on the size of the database, but only needs to support the single homomorphic encryption scheme to decrypt the circuit depth. Based on this hybrid homomorphic encryption retrieval model, the efficiency of homomorphic privacy information retrieval model can be greatly improved.