The widespread adoption of Internet of Things (IoT) technology has introduced new cybersecurity challenges. Encryption services are being offloaded to cloud and fog platforms to mitigate these risks. Encryption as a Service (EaaS) emerges as a remedy, offering cryptographic solutions tailored to the resource constraints of IoT devices. This study thoroughly examines existing EaaS platforms, categorizing them based on encryption algorithms and service offerings. Additionally, we outline various EaaS architecture types depending on the placement of key components. Practical implementations of these platforms are explored through different testbeds. A key focus lies in dissecting the challenges that EaaS faces, particularly in the context of IoT, while suggesting potential remedies. This work stands out as an all-encompassing exploration, bridging the gap left by previous surveys.
4 February 2022 in IEEE Transactions on Knowledge and Data Engineering
The International Classification of Diseases (ICD) is a standard for categorizing physical conditions, which has been widely used for analyzing clinical data and monitoring health issues. Manual ICD coding takes a long time and is vulnerable to errors, so people pay more and more attention to the application of deep neural networks in ICD automatic coding. However, there is still no comprehensive review of these studies and prospects for further research. This paper is not limited to the study of deep neural networks, but gives a formal definition of ICD coding problems, and then systematically reviews the existing literature on how to design deep neural networks to address the four major challenges of ICD coding tasks. This paper also summarizes the public data sets and future research directions, to provide a guidance for the research of ICD coding in medical field.
The rise of artificial intelligence applications has led to a surge in Internet of Things (IoT) research. Biometric recognition methods are extensively used in IoT access control due to their convenience. To address the limitations of unimodal biometric recognition systems, we propose an attention-based multimodal biometric recognition (AMBR) network that incorporates attention mechanisms to extract biometric features and fuse the modalities effectively. Additionally, to overcome issues of data privacy and regulation associated with collecting training data in IoT systems, we utilize Federated Learning (FL) to train our model This collaborative machine-learning approach enables data parties to train models while preserving data privacy. Our proposed approach achieves 0.68%, 0.47%, and 0.80% Equal Error Rate (EER) on the three VoxCeleb1 official trial lists, performs favorably against the current methods, and the experimental results in FL settings illustrate the potential of AMBR with an FL approach in the multimodal biometric recognition scenario.
A detection model of Internet of Things encrypted traffic based on edge intelligence is proposed in the paper, which can reduce the communication times of distributed Internet of Things gateways in the process of edge intelligence as well as the encrypted traffic detection model establishment time, in order to solve the problems that it is difficult to carry out efficient classification and accurate identification of the encrypted traffic of Internet of Things. In this paper, four new classification and identification methods for encrypted traffic are put forward, namely time-sequence behavior analysis, dynamic behavior analysis, key behavior analysis and two-round filtering analysis. The experimental results show that when the sample size is 1600, the encrypted traffic detection model establishment time is less than 100 seconds, and the accuracy of all the four new traffic classification methods is more than 92% and the recall rates of them are more than 83%.
13 May 2025 in ACM Transactions on Intelligent Systems and Technology
This paper introduces AEKG4APT, an APT Knowledge Graph (KG) enhanced by Large Language Models (LLMs), as a way to deal with the cybersecurity problems caused by Advanced Persistent Threats (APTs). The core of AEKG4APT lies in the combined application of LLMs, Cyber Threat Intelligence (CTI), and KG. The first part of the paper goes into great detail about how the AEKG4APT was constructed, including its ontology schema, data sources, and dataset features. There are also statistics on the AEKG4APT’s nodes, relationships, and key attributes. Secondly, it was shown how to utilize LLMs and public sandboxes for the collection and analysis of CTI Additionally, tests that compare traditional deep learning models to LLM methods show that LLM is both more efficient and more accurate at extracting information. Subsequently, the Decision Making Trial and Evaluation Laboratory - Interpretive Structural Modeling (DEMATEL-ISM) analytical method was introduced to identify and analyse the factors and their interrelationships within the AEKG4APT data, thereby revealing the key dependencies and influence paths within the data structure. Experiments were designed to demonstrate its applications in modeling, computing, and obtaining interpretable computational results on AEKG4APT. In addition, this paper also explores the dynamic expansion capabilities of AEKG4APT, including data expansion, schema expansion, and permanent maintenance strategies, to address the evolving APT threats. Finally, this paper summarizes the competitiveness and application value of AEKG4APT by comparing it with other CTI KGs and platforms in academia and industry, demonstrating its extensive application potential in the field of cybersecurity.
Encrypted traffic classification is a crucial part of privacy-preserving research. With the great success of artificial intelligence technology in fields such as image recognition and natural language processing, how to classify encrypted traffic based on AI technology has become an attractive topic in information security. With good generalization ability and high training accuracy, pre-training-based encrypted traffic classification methods have become the first option. The accuracy of this type of method depends highly on the fine-tuning model. However, it is a challenge for existing fine-tuned models to effectively integrate the representation of packet and byte features extracted via pre-training. A novel fine-tuning model, LAMBERT, is proposed in this article. By introducing an attention mechanism to capture the relationship between BiGRU and byte sequences, LAMBERT not only effectively improves the sequence loss phenomenon of BiGRU but also improves the processing performance of encrypted stream classification. LAMBERT can quickly and accurately classify multiple types of encrypted traffic. The experimental results show that our model performs well on datasets with uneven sample distribution, no pre-training, and large sample classification. LAMBERT was tested on four datasets, namely, ISCX-VPN-Service, ISCX-VPN-APP, USTC-TFC and CSTNET-TLS 1.3, and the F1 scores reached 99.15%, 99.52%, 99.30%, and 97.41%, respectively.