Fund allocation has been an increasingly important problem in the financial domain. In reality, we aim to allocate the funds to buy certain assets within a certain future period. Naive solutions such as prediction-only or Predict-then-Optimize approaches suffer from goal mismatch. Additionally, the introduction of the SOTA time series forecasting model inevitably introduces additional uncertainty in the predicted result. To solve both problems mentioned above, we introduce a Risk-aware Time-Series Predict-and-Allocate (RTS-PnO) framework, which holds no prior assumption on the forecasting models. Such a framework contains three features: (i) end-to-end training with objective alignment measurement(ii) adaptive forecasting uncertainty calibration, and (iii) agnostic towards forecasting models. The evaluation of RTS-PnO is conducted over both online and offline experiments. For offline experiments, eight datasets from three categories of financial applications are used: Currency, Stock, and Cryptos. RTS-PnO consistently outperforms other competitive baselines. The online experiment is conducted on the Cross-Border Payment business at FiT, Tencent, and an 8.4% decrease in regret is witnessed when compared with the product-line approach. The code for the offline experiment is available.

With the application of wireless sensor network (WSN) in healthcare field, online sharing of medical data has attracted more and more attention. However, wearable sensor nodes are limited in energy, storage space and data processing capacity, which largely restricts their deployment in resource demand application scenarios. Fortunately, cloud storage services can enrich the capabilities of wearable sensors and provide an effective method for people to share data within a group. However, as medical data directly relates to patients' health and privacy information, ensuring the integrity and privacy of medical records stored in cloud servers becomes a key issue to be urgently solved. Many public data auditing schemes have been put forward to address the above issues. Unfortunately, most of them have security vulnerabilities or poor functionality and performance. In this paper, we come up with a secure and efficient certificateless public auditing scheme for cloud-assisted medical WSNs, which not only supports dynamic data sharingand privacy protection, but also achieves efficient group user revocation. Security analysis and performance evaluation demonstrate that our scheme significantly reduce the total computation cost while achieving a higher security level. Compared with other related schemes, our new proposal is more suitable for group user data sharing in cloud-assisted medical WSNs.

This paper tackles automated categorization of Age-related Macular Degeneration (AMD), a common macular disease among people over 50. Previous research efforts mainly focus on AMD categorization with a single-modal input, let it be a color fundus photograph (CFP) or an OCT B-scan image. By contrast, we consider AMD categorization given a multi-modal input, a direction that is clinically meaningful yet mostly unexplored. Contrary to the prior art that takes a traditional approach of feature extraction plus classifier training that cannot be jointly optimized, we opt for end-to-end multi-modal Convolutional Neural Networks (MM-CNN). Our MM-CNN is instantiated by a two-stream CNN, with spatially-invariant fusion to combine information from the CFP and OCT streams. In order to visually interpret the contribution of the individual modalities to the final prediction, we extend the class activation mapping (CAM) technique to the multi-modal scenario. For effective training of MM-CNN, we develop two data augmentation methods. One is GAN-based CFP/OCT image synthesis, with our novel use of CAMs as conditional input of a high-resolution image-to-image translation GAN. The other method is Loose Pairing, which pairs a CFP image and an OCT image on the basis of their classes instead of eye identities. Experiments on a clinical dataset consisting of 1,094 CFP images and 1,289 OCT images acquired from 1,093 distinct eyes show that the proposed solution obtains better F1 and Accuracy than multiple baselines for multi-modal AMD categorization. Code and data are available at https://github.com/li-xirong/mmc-amd.

Certificateless public key cryptosystem solves both the complex certificate management problem in the public key cryptosystem based on the PKI and the key escrow issue in the public key cryptosystem based on identity. The aggregator can compress n different signatures with respect to n messages from n signers into an aggregate signature, which can help communication equipments to save a lot of bandwidth and computing resources. Therefore, the certificateless aggregate signature (CLAS) scheme is particularly well suited to address secure routing authentication issues in resource-constrained vehicular ad hoc networks. Unfortunately, most of the existing CLAS schemes have problems with security vulnerabilities or high computation and communication overheads. To avoid the above issues and better solve the secure routing authentication problem in vehicular ad hoc networks, we present a new CLAS scheme and give the formal security proof of our scheme under the CDH assumption in the random oracle model. We then evaluate the performance of our proposed CLAS scheme, and the results demonstrate that our proposal is more practical in resource-constrained vehicular ad hoc networks.

With the popularization of wireless communication and smart devices in the medical field, mobile medicine has attracted more and more attention because it can break through the limitations of time, space, and objects and provide more efficient and quality medical services. However, the characteristics of a mobile smart medical network make it more susceptible to security threats such as data integrity damage and privacy leakage than those of traditional wired networks. In recent years, many digital signature schemes have been proposed to alleviate some of these challenges. Unfortunately, traditional digital signatures cannot meet the diversity and privacy requirements of medical data applications. In response to this problem, this paper uses the unique security attributes of sanitizable signatures to carry out research on the security and privacy protection of medical data and proposes a data security and privacy protection scheme suitable for smart mobile medical scenarios. Security analysis and performance evaluation show that our new scheme effectively guarantees data security and user privacy while greatly reducing computation and communication costs, making it especially suitable for mobile smart medical application scenarios.

With the application of sensor technology in the field of healthcare, online data sharing in healthcare industry attracts more and more attention since it has many advantages, such as high efficiency, low latency, breaking the geographical location, and time constraints. However, due to the direct involvement of patient health information, the privacy and integrity of medical data have become a matter of much concern to the healthcare industry. To retain data privacy and integrity, a number of digital signature schemes have been introduced in recent years. Unfortunately, most of them suffer serious security attacks and do not perform well in terms of computation overhead and communication overhead. Very recently, Pankaj Kumar et al. proposed a certificateless aggregate signature scheme for healthcare wireless sensor network. They claimed that their signature scheme was able to withstand a variety of attacks. However, in this paper, we find that their scheme fails to achieve its purpose since it is vulnerable to signature forgery attack and give the detailed attack process. Then, we propose a new certificateless aggregate signature scheme to fix the security flaws and formally prove that our proposed scheme is secure under the computationally hard Diffie-Hellman assumption. Security analysis and performance evaluation demonstrate that the security of our proposal is improved while reducing the computation cost. Compared with Pankaj Kumar et al.'s scheme, our proposed scheme is more efficient and suitable for the healthcare wireless sensor networks (HWSNs) to maintain security at various levels.