Distributed Denial of Service (DDoS) attacks, advanced persistent threats, and malware actively compromise the availability and security of Internet services. Thus, this paper proposes an intelligent agent system for detecting DDoS attacks using automatic feature extraction and selection. We used dataset CICDDoS2019, a custom-generated dataset, in our experiment, and the system achieved a 99.7% improvement over state-of-the-art machine learning-based DDoS attack detection techniques. We also designed an agent-based mechanism that combines machine learning techniques and sequential feature selection in this system. The system learning phase selected the best features and reconstructed the DDoS detector agent when the system dynamically detected DDoS attack traffic. By utilizing the most recent CICDDoS2019 custom-generated dataset and automatic feature extraction and selection, our proposed method meets the current, most advanced detection accuracy while delivering faster processing than the current standard.

Storage is a promising application for permission-less blockchains. Before blockchain, cloud storage was hosted by a trusted service provider. The centralized system controls the permission of the data access. In web3, users own their data. Data must be encrypted in a permission-less decentralized storage network, and the permission control should be pure cryptographic. Proxy re-encryption (PRE) is ideal for cryptographic access control, which allows a proxy to transfer Alice’s ciphertext to Bob with Alice’s authorization. The encrypted data are stored in several copies for redundancy in a permission-less decentralized storage network. The redundancy suffers from the outsourcing attack. The malicious resource provider may fetch the content from others and respond to the verifiers. This harms data integrity security. Thus, proof-of-replication (PoRep) must be applied to convince the user that the storage provider is using dedicated storage. PoRep is an expensive operation that encodes the original content into a replication. Existing PRE schemes cannot satisfy PoRep, as the cryptographic permission granting generates an extra ciphertext. A new ciphertext would result in several expensive replication operations. We searched most of the PRE schemes for the combination of the cryptographic methods to avoid transforming the ciphertext. Therefore, we propose a new PRE scheme. The proposed scheme does not require the proxy to transfer the ciphertext into a new one. It reduces the computation and operation time when allowing a new user to access a file. Furthermore, the PRE scheme is CCA (chosen-ciphertext attack) security and only needs one key pair.

Metastasis detection in lymph nodes via microscopic examination of histopathological images is one of the most crucial diagnostic procedures for breast cancer staging. The manual analysis is extremely labor-intensive and time-consuming because of complexities and diversities of histopathology images. Deep learning has been utilized in automatic cancer metastasis detection in recent years. Due to the huge size of whole-slide images, most existing approaches split each image into smaller patches and simply treat these patches independently, which ignores the spatial correlations among them. To solve this problem, this paper proposes an effective spatially sensitive learning framework for cancer metastasis detection in whole-slide images. Moreover, a novel spatial loss function is designed to ensure the consistency of prediction over neighboring patches. Specifically, through incorporating long short-term memory and spatial loss constraint on top of a convolutional neural network feature extractor, the proposed method can effectively learn both the appearance of each patch and spatial relationships between adjacent image patches. With the standard back-propagation algorithm, the whole framework can be trained in an end-to-end way. Finally, the regions with high tumor probability in the resulting probability map are the metastasis locations. Extensive experiments on the benchmark Camelyon 2016 Grand Challenge dataset show the effectiveness of the proposed approach with respect to state-of-the-art competitors. The obtained precision, recall, and balanced accuracy are 0.9565, 0.9167, and 0.9458, respectively. It is also demonstrated that the proposed approach can provide more accurate detection results and is helpful for early diagnosis of cancer metastasis.

The metastasis detection in lymph nodes via microscopic examination of H&E stained histopathological images is one of the most crucial diagnostic procedures for breast cancer staging. The manual analysis is extremely labor-intensive and time-consuming because of complexities and diversities of histopathological images. Deep learning has been utilized in automatic cancer metastasis detection in recent years. The success of supervised deep learning is credited to a large labeled dataset, which is hard to obtain in medical image analysis. Contrastive learning, a branch of self-supervised learning, can help in this aspect through introducing an advanced strategy to learn discriminative feature representations from unlabeled images. In this paper, we propose to improve breast cancer metastasis detection through self-supervised contrastive learning, which is used as an accessional task in the detection pipeline, allowing a feature extractor to learn more valuable representations, even if there are fewer annotation images. Furthermore, we extend the proposed approach to exploit unlabeled images in a semi-supervised manner, as self-supervision does not need labeled data at all. Extensive experiments on the benchmark Camelyon2016 Grand Challenge dataset demonstrate that self-supervision can improve cancer metastasis detection performance leading to state-of-the-art results.

The authentication between smart meters and Neighbourhood Area Communication Network (NAN) gateways is a critical issue due to various types of side channel attacks. To address this, a new protocol called Lightweight Leakage-Resilient Authentication Key Exchange (LLRA) was proposed for smart meters. LLRA incorporates continuous after-the-fact leakage-resilient property. Furthermore, extended BPR (CLR-eBPR) security model and extended GNY (CLR-eGNY) logic were introduced. Through provable security analysis, logic analysis, and practical performance evaluations, we demonstrated that LLRA effectively mitigates side-channel attacks while maintaining minimum authentication delay and energy consumption for the computing devices used in smart meters and NAN gateways. Compared to benchmark protocols, the authentication delay of LLRA was decreased by at least 14%; in addition, the energy consumption of LLRA was decreased by at least 7%.