Blockchain-Assisted Reputation Management Scheme for Internet of Vehicles.

With the rapid development of Internet of Vehicles (IoV), particularly the introduction of Mobile Edge Computing (MEC), vehicles can efficiently share data with one another. However, edge computing nodes are vulnerable to various network attacks, posing security risks to data storage and sharing. Moreover, the presence of abnormal vehicles during the sharing process poses significant security threats to the entire network. To address these issues, this paper proposes a novel reputation management scheme, which proposes an improved multi-source multi-weight subjective logic algorithm. This algorithm fuses the direct and indirect opinion feedback of nodes through the subjective logic trust model while considering factors such as event validity, familiarity, timeliness, and trajectory similarity. Vehicle reputation values are periodically updated, and abnormal vehicles are identified through reputation thresholds. Finally, blockchain technology is employed to ensure the security of data storage and sharing. By analyzing real vehicle trajectory datasets, the algorithm is proven to effectively improve the differentiation and detection rate of abnormal vehicles.

Subjective logic as a complementary tool to meta-analysis to explicitly address second-order uncertainty in research findings: A case from infant studies.

Any experiment brings about results and conclusions that necessarily have a component of uncertainty. Many factors influence the degree of this uncertainty, yet they can be overlooked when drawing conclusions from a body of research. Here, we showcase how subjective logic could be employed as a complementary tool to meta-analysis to incorporate the chosen sources of uncertainty into the answer that researchers seek to provide to their research question. We illustrate this approach by focusing on a body of research already meta-analyzed, whose overall aim was to assess if human infants prefer prosocial agents over antisocial agents. We show how each finding can be encoded as a subjective opinion, and how findings can be aggregated to produce an answer that explicitly incorporates uncertainty. We argue that a core feature and strength of this approach is its transparency in the process of factoring in uncertainty and reasoning about research findings. Subjective logic promises to be a powerful complementary tool to incorporate uncertainty explicitly and transparently in the evaluation of research.

Dual consistency regularization with subjective logic for semi-supervised medical image segmentation.

Semi-supervised learning plays a vital role in computer vision tasks, particularly in medical image analysis. It significantly reduces the time and cost involved in labeling data. Current methods primarily focus on consistency regularization and the generation of pseudo labels. However, due to the model's poor awareness of unlabeled data, aforementioned methods may misguide the model. To alleviate this problem, we propose a dual consistency regularization with subjective logic for semi-supervised medical image segmentation. Specifically, we introduce subjective logic into our semi-supervised medical image segmentation task to estimate uncertainty, and based on the consistency hypothesis, we construct dual consistency regularization under weak and strong perturbations to guide the model's learning from unlabeled data. To evaluate the performance of the proposed method, we performed experiments on three widely used datasets: ACDC, LA, and Pancreas. Experiments show that the proposed method achieved improvement compared with other state-of-the-art (SOTA) methods.

There Is Hope After All: Quantifying Opinion and Trustworthiness in Neural Networks.

Artificial Intelligence (AI) plays a fundamental role in the modern world, especially when used as an autonomous decision maker. One common concern nowadays is "how trustworthy the AIs are." Human operators follow a strict educational curriculum and performance assessment that could be exploited to quantify how much we entrust them. To quantify the trust of AI decision makers, we must go beyond task accuracy especially when facing limited, incomplete, misleading, controversial or noisy datasets. Toward addressing these challenges, we describe DeepTrust, a Subjective Logic (SL) inspired framework that constructs a probabilistic logic description of an AI algorithm and takes into account the trustworthiness of both dataset and inner algorithmic workings. DeepTrust identifies proper multi-layered neural network (NN) topologies that have high projected trust probabilities, even when trained with untrusted data. We show that uncertain opinion of data is not always malicious while evaluating NN's opinion and trustworthiness, whereas the disbelief opinion hurts trust the most. Also trust probability does not necessarily correlate with accuracy. DeepTrust also provides a projected trust probability of NN's prediction, which is useful when the NN generates an over-confident output under problematic datasets. These findings open new analytical avenues for designing and improving the NN topology by optimizing opinion and trustworthiness, along with accuracy, in a multi-objective optimization formulation, subject to space and time constraints.