Towards trustworthy multi-modal motion prediction:Holistic evaluation and interpretability of outputs

Predicting the motion of other road agents enables autonomous vehicles to perform safe and efficient path planning.This task is very complex,as the behaviour of road agents depends on many factors and the number of possible future trajectories can be consid-erable(multi-modal).Most prior approaches proposed to address multi-modal motion prediction are based on complex machine learning systems that have limited interpret-ability.Moreover,the metrics used in current benchmarks do not evaluate all aspects of the problem,such as the diversity and admissibility of the output.The authors aim to advance towards the design of trustworthy motion prediction systems,based on some of the re-quirements for the design of Trustworthy Artificial Intelligence.The focus is on evaluation criteria,robustness,and interpretability of outputs.First,the evaluation metrics are comprehensively analysed,the main gaps of current benchmarks are identified,and a new holistic evaluation framework is proposed.Then,a method for the assessment of spatial and temporal robustness is introduced by simulating noise in the perception system.To enhance the interpretability of the outputs and generate more balanced results in the proposed evaluation framework,an intent prediction layer that can be attached to multi-modal motion prediction models is proposed.The effectiveness of this approach is assessed through a survey that explores different elements in the visualisation of the multi-modal trajectories and intentions.The proposed approach and findings make a significant contribution to the development of trustworthy motion prediction systems for autono-mous vehicles,advancing the field towards greater safety and reliability.

CrossLinkNet: An Explainable and Trustworthy AI Framework for Whole-Slide Images Segmentation

In the intelligent medical diagnosis area,Artificial Intelligence(AI)’s trustworthiness,reliability,and interpretability are critical,especially in cancer diagnosis.Traditional neural networks,while excellent at processing natural images,often lack interpretability and adaptability when processing high-resolution digital pathological images.This limitation is particularly evident in pathological diagnosis,which is the gold standard of cancer diagnosis and relies on a pathologist’s careful examination and analysis of digital pathological slides to identify the features and progression of the disease.Therefore,the integration of interpretable AI into smart medical diagnosis is not only an inevitable technological trend but also a key to improving diagnostic accuracy and reliability.In this paper,we introduce an innovative Multi-Scale Multi-Branch Feature Encoder(MSBE)and present the design of the CrossLinkNet Framework.The MSBE enhances the network’s capability for feature extraction by allowing the adjustment of hyperparameters to configure the number of branches and modules.The CrossLinkNet Framework,serving as a versatile image segmentation network architecture,employs cross-layer encoder-decoder connections for multi-level feature fusion,thereby enhancing feature integration and segmentation accuracy.Comprehensive quantitative and qualitative experiments on two datasets demonstrate that CrossLinkNet,equipped with the MSBE encoder,not only achieves accurate segmentation results but is also adaptable to various tumor segmentation tasks and scenarios by replacing different feature encoders.Crucially,CrossLinkNet emphasizes the interpretability of the AI model,a crucial aspect for medical professionals,providing an in-depth understanding of the model’s decisions and thereby enhancing trust and reliability in AI-assisted diagnostics.

Uncertainty-Aware Deep Learning: A Promising Tool for Trustworthy Fault Diagnosis

Recently,intelligent fault diagnosis based on deep learning has been extensively investigated,exhibiting state-of-the-art performance.However,the deep learning model is often not truly trusted by users due to the lack of interpretability of“black box”,which limits its deployment in safety-critical applications.A trusted fault diagnosis system requires that the faults can be accurately diagnosed in most cases,and the human in the deci-sion-making loop can be found to deal with the abnormal situa-tion when the models fail.In this paper,we explore a simplified method for quantifying both aleatoric and epistemic uncertainty in deterministic networks,called SAEU.In SAEU,Multivariate Gaussian distribution is employed in the deep architecture to compensate for the shortcomings of complexity and applicability of Bayesian neural networks.Based on the SAEU,we propose a unified uncertainty-aware deep learning framework(UU-DLF)to realize the grand vision of trustworthy fault diagnosis.Moreover,our UU-DLF effectively embodies the idea of“humans in the loop”,which not only allows for manual intervention in abnor-mal situations of diagnostic models,but also makes correspond-ing improvements on existing models based on traceability analy-sis.Finally,two experiments conducted on the gearbox and aero-engine bevel gears are used to demonstrate the effectiveness of UU-DLF and explore the effective reasons behind.

Analysis of system trustworthiness based on information flow noninterference theory

The trustworthiness analysis and evaluation are the bases of the trust chain transfer. In this paper the formal method of trustworthiness analysis of a system based on the noninterfer- ence （NI） theory of the information flow is studied. Firstly, existing methods cannot analyze the impact of the system states on the trustworthiness of software during the process of trust chain trans- fer. To solve this problem, the impact of the system state on trust- worthiness of software is investigated, the run-time mutual interfer- ence behavior of software entitles is described and an interference model of the access control automaton of a system is established. Secondly, based on the intransitive noninterference （INI） theory, a formal analytic method of trustworthiness for trust chain transfer is proposed, providing a theoretical basis for the analysis of dynamic trustworthiness of software during the trust chain transfer process. Thirdly, a prototype system with dynamic trustworthiness on a plat- form with dual core architecture is constructed and a verification algorithm of the system trustworthiness is provided. Finally, the monitor hypothesis is extended to the dynamic monitor hypothe- sis, a theorem of static judgment rule of system trustworthiness is provided, which is useful to prove dynamic trustworthiness of a system at the beginning of system construction. Compared with previous work in this field, this research proposes not only a formal analytic method for the determination of system trustworthiness, but also a modeling method and an analysis algorithm that are feasible for practical implementation.

Access Request Trustworthiness in Weighted Access Control Framework

Weighted factor is given to access eontrol policies to express the importanceof policy and its effect on access control decision. According to this weighted access controlframework, a trustworthiness model for aceess request is also given. In this model, we give themeasure of trustworthiness factor to access request- by using some idea of uncertainty reasoning ofexpert system, present and prove the parallel propagation formula of request trustworthiness factoramong multiple policies, and get thefinal trustworthiness factor to decide whether authorizing. Inthis model, authorization decision is given according to the calculation of request trustworthinessfactor, which is more understandable, more suitable for real requirement and more powerfulforsecurity enhancement than traditional methods. Meanwhile the finer access control granularity isanother advantage.

Component-Based Software Trustworthiness Fuzzy Analytic Hierarchy Process Model

For a more accurate and comprehensive assessment of the trustworthiness of component-based soft- ware system, the fuzzy analytic hierarchy process is introduced to establish the analysis model. Combine qualitative and quantitative analyses, the impacts to overall trustworthiness by the different types of components are distinguished. Considering the coupling relationship between components, dividing the system into several layers from target layer to scheme layer, evaluating the scheme advantages disadvantages by group decision-making, the trustworthiness of a typical J2EE structured component-based software is assessed. The trustworthiness asses model of the software components provides an effective methods of operation.

Hash Tree Based Trustworthiness Verification Mechanism in Virtual Environment

The trustworthiness of virtual machines is a big security issue in cloud computing. In this paper, we aimed at designing a practical trustworthiness mechanism in virtual environment. With the assist of a third certificate agent, the cloud user generates a trust base and extends it to its VMs. For each service running on the VM, a hash value is generated from all the necessary modules, and these hash values are organized and maintained with a specially designed hash tree whose root is extended from the user's trust base. Before the VM loads a service, the hash tree is verified from the coordinated hash value to check the trustworthiness of the service.

Adversarial Attack-Based Robustness Evaluation for Trustworthy AI

Artificial Intelligence(AI)technology has been extensively researched in various fields,including the field of malware detection.AI models must be trustworthy to introduce AI systems into critical decisionmaking and resource protection roles.The problem of robustness to adversarial attacks is a significant barrier to trustworthy AI.Although various adversarial attack and defense methods are actively being studied,there is a lack of research on robustness evaluation metrics that serve as standards for determining whether AI models are safe and reliable against adversarial attacks.An AI model’s robustness level cannot be evaluated by traditional evaluation indicators such as accuracy and recall.Additional evaluation indicators are necessary to evaluate the robustness of AI models against adversarial attacks.In this paper,a Sophisticated Adversarial Robustness Score(SARS)is proposed for AI model robustness evaluation.SARS uses various factors in addition to the ratio of perturbated features and the size of perturbation to evaluate robustness accurately in the evaluation process.This evaluation indicator reflects aspects that are difficult to evaluate using traditional evaluation indicators.Moreover,the level of robustness can be evaluated by considering the difficulty of generating adversarial samples through adversarial attacks.This paper proposed using SARS,calculated based on adversarial attacks,to identify data groups with robustness vulnerability and improve robustness through adversarial training.Through SARS,it is possible to evaluate the level of robustness,which can help developers identify areas for improvement.To validate the proposed method,experiments were conducted using a malware dataset.Through adversarial training,it was confirmed that SARS increased by 70.59%,and the recall reduction rate improved by 64.96%.Through SARS,it is possible to evaluate whether an AI model is vulnerable to adversarial attacks and to identify vulnerable data types.In addition,it is expected that improved models can be achieved by improving resistance to adversarial attacks via methods such as adversarial training.

Reasoning about Software Trustworthiness with Derivation Trees

In order to analyze the trustworthiness of complex software systems,we propose a model of evidence-based software trustworthiness called trustworthiness derivation tree(TDT).The basic idea of constructing a TDT is to refine main properties into key ingredients and continue the refinement until basic facts such as evidences are reached.The skeleton of a TDT can be specified by a set of rules,which are convenient for automated reasoning in Prolog.We develop a visualization tool that can construct the skeleton of a TDT by taking the rules as input,and allow a user to edit the TDT in a graphical user interface.In a software development life cycle,TDTs can serve as a communication means for different stakeholders to agree on the properties about a system in the requirement analysis phase,and they can be used for deductive reasoning so as to verify whether the system achieves trustworthiness in the product validation phase.We have piloted the approach of using TDTs in more than a dozen real scenarios of software development.Indeed,using TDTs helped us to discover and then resolve some subtle problems.

Analysis of Software Trustworthiness Based on FAHP-CRITIC Method

Software trustworthiness includes many attributes.Reasonable weight allocation of trustworthy at-tributes plays a key role in the software trustworthiness measurement.In practical application,attribute weight usually comes from experts'evaluation to attributes and hidden information derived from attributes.Therefore,when the weight of attributes is researched,it is necessary to consider weight from subjective and objective as-pects.First,a novel weight allocation method is proposed by combining the fuzzy analytical hierarchy process(FAHP)method and the criteria importance though intercrieria correlation(CRITIC)method.Second,based on the weight allocation method,the trustworthiness measurement models of component-based software are estab-lished according to the seven combination structures of components.Third,the model reasonability is verified via proving some metric criteria.Finally,a case is carried out.According to the comparison with other models,the result shows that the model has the advantage of utilizing hidden information fully and analyzing the com-bination of components effectively.It is an important guide for measuring the trustworthiness measurement of component-based software.

A personalized trustworthy service selection method

A personalized trustworthy service selection method is proposed to fully express the features of trust, emphasize the importance of user preference and improve the trustworthiness of service selection. The trustworthiness of web service is defined as customized multi-dimensional trust metrics and the user preference is embodied in the weight of each trust metric. A service selection method combining AHP （analytic hierarchy process） and PROMETHEE （preference ranking organization method for enrichment evaluations） is proposed. AHP is used to determine the weights of trust metrics according to users＇ preferences. Hierarchy and pairwise comparison matrices are constructed. The weights of trust metrics are derived from the highest eigenvalue and eigenvector of the matrix. to obtain the final rank of candidate services. The preference functions are defined according to the inherent characteristics of the trust metrics and net outranking flows are calculated. Experimental results show that the proposed method can effectively express users＇ personalized preferences for trust metrics, and the trustworthiness of service ranking and selection is efficiently improved.

Trustworthy Metrics Models for Internetware

To measure the trustworthiness of Intemetware, we need to understand the existing problems and design appropriate trustworthy metrics. The developing and running system of Internetware is analyzed in terms of process, keystone, methods and techniques. According to the main related factors of Internetware trustworthiness, two important models, namely trustworthy metrics hierarchy model of components （TMHMC） with computing steps and local-global trustworthy metrics model of platform （LGTMMP） with algorithm respectively, are employed to evaluate the internal and external trustworthiness of Internetware benefiting for the development of Internetware.

A new type of blockchain for secure message exchange in VANET

In the Vehicular Ad-hoc NETworks(VANET),the collection and dissemination of life-threatening traffic event information by vehicles are of utmost importance.However,traditional VANETs face several security issues.We propose a new type of blockchain to resolve critical message dissemination issues in the VANET.We create a local blockchain for real-world event message exchange among vehicles within the boundary of a country,which is a new type of blockchain suitable for the VANET.We present a public blockchain that stores the node trustworthiness and message trustworthiness in a distributed ledger that is appropriate for secure message dissemination.

Screening for scoliosis-New recommendations,old dilemmas,no straight solutions

This opinion review considers the prevailing question of whether to screen or notto screen for adolescent idiopathic scoliosis. New and improved standards ofpeople-oriented care and person-centredness, as well as improved principles ofpreventive screening and guideline development, have been postulated andimplemented in health care systems and cultures. Recommendations addressingscreening for scoliosis differ substantially, in terms of their content, standards ofdevelopment and screening principles. Some countries have discontinued issuingrecommendations. In the last decade, a number of updated and newrecommendations and statements have been released. Systematically developedguidelines and recommendations are confronted by consensus and opinion-basedstatements. The dilemmas and discrepancies prevail. The arguments concentrateon the issues of the need for early detection through screening in terms of theeffectiveness of early treatment, on costs and cost-effectiveness issues, scientificand epidemiologic value of screenings, and the credibility of the sources ofevidence. The problem matter is of global scale and applies to millions of people.It regards clinical and methodological dilemmas, but also the matter of vulnerableand fragile time of adolescence and, more generally, children’s rights. Thedecisions need to integrate people’s values and preferences – screening tests needto be acceptable to the population, and treatments need to be acceptable forpatients. Therefore we present one more crucial, but underrepresented in thediscussion, issue of understanding and implementation of the contemporaryprinciples of person-centred care, standards of preventive screening, andguideline development, in the context of screening for scoliosis.

DIV： Dynamic Integrity Validation Framework for Detecting Compromises on Virtual Machine Based Cloud Services in Real Time

with the increasing popularity of cloud services,attacks on the cloud infrastructure also increase dramatically.Especially,how to monitor the integrity of cloud execution environments is still a difficult task.In this paper,a real-time dynamic integrity validation(DIV) framework is proposed to monitor the integrity of virtual machine based execution environments in the cloud.DIV can detect the integrity of the whole architecture stack from the cloud servers up to the VM OS by extending the current trusted chain into virtual machine's architecture stack.DIV introduces a trusted third party(TTP) to collect the integrity information and detect remotely the integrity violations on VMs periodically to avoid the heavy involvement of cloud tenants and unnecessary information leakage of the cloud providers.To evaluate the effectiveness and efficiency of DIV framework,a prototype on KVM/QEMU is implemented,and extensive analysis and experimental evaluation are performed.Experimental results show that the DIV can efficiently validate the integrity of files and loaded programs in real-time,with minor performance overhead.

SATVPC:Secure-agent-based trustworthy virtual private cloud model in open computing environments

Private clouds and public clouds are turning mutually into the open integrated cloud computing environment,which can aggregate and utilize WAN and LAN networks computing,storage,information and other hardware and software resources sufficiently,but also bring a series of security,reliability and credibility problems.To solve these problems,a novel secure-agent-based trustworthy virtual private cloud model named SATVPC was proposed for the integrated and open cloud computing environment.Through the introduction of secure-agent technology,SATVPC provides an independent,safe and trustworthy computing virtual private platform for multi-tenant systems.In order to meet the needs of the credibility of SATVPC and mandate the trust relationship between each task execution agent and task executor node suitable for their security policies,a new dynamic composite credibility evaluation mechanism was presented,including the credit index computing algorithm and the credibility differentiation strategy.The experimental system shows that SATVPC and the credibility evaluation mechanism can ensure the security of open computing environments with feasibility.Experimental results and performance analysis also show that the credit indexes computing algorithm can evaluate the credibilities of task execution agents and task executor nodes quantitatively,correctly and operationally.

SemTrust: A Semantic Reputation System in P2P-Based Semantic Web

A reputation mechanism is introduced in P2P- based Semantic Web to solve the problem of lacking trust. It enables Semantic Web to utilize reputation information based on semantic similarity of peers in the network. This approach is evaluated in a simulation of a content sharing system and the experiments show that the system with reputation mechanism outperforms the system without it.

User preferences-aware recommendation for trustworthy cloud services based on fuzzy clustering

The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service among a large amount of service candidates. A novel user preferences-aware recommendation approach for trustworthy services is presented. For describing the requirements of new users in different application scenarios, user preferences are identified by usage preference, trust preference and cost preference. According to the similarity analysis of usage preference between consumers and new users, the candidates are selected, and these data about service trust provided by them are calculated as the fuzzy comprehensive evaluations. In accordance with the trust and cost preferences of new users, the dynamic fuzzy clusters are generated based on the fuzzy similarity computation. Then, the most suitable services can be selected to recommend to new users. The experiments show that this approach is effective and feasible, and can improve the quality of services recommendation meeting the requirements of new users in different scenario.

Multiway Dynamic Trust Chain Model on Virtual Machine for Cloud Computing

This paper sums up four security factors after analyzing co-residency threats caused by the special multitenant environment in the cloud.To secure the factors,a multiway dynamic trust chain transfer model was proposed on the basis of a measurement interactive virtual machine and current behavior to protect the integrity of the system.A trust chain construction module is designed in a virtual machine monitor.Through dynamic monitoring,it achieves the purpose of transferring integrity between virtual machine.A cloud system with a trust authentication function is implemented on the basis of the model,and its practicability is shown.

Research and Analysis of Structural Hole and Matching Coefficient

Measure is a map from the reality or experimental world to the mathematical world, through which people can more easily understand the properties of entities and the relationship between them. But the traditional software measurement methods have been unable to effectively measure this large-scale software. Therefore, trustworthy measurement gives an accurate measurement to these emerging features, providing valuable perspectives and different research dimensions to understand software systems. The paper introduces the complex network theory to software measurement methods and proposes a statistical measurement methodology. First we study the basic parameters of the complex network, and then introduce two new measurement parameters: structural holes, matching coefficient.