Biblio

In the Internet of Vehicles (IoV) paradigm, a model owner is able to leverage on the enhanced capabilities of Intelligent Connected Vehicles (ICV) to develop promising Artificial Intelligence (AI) based applications, e.g., for traffic efficiency. However, in some cases, a model owner may have insufficient data samples to build an effective AI model. To this end, we propose a Federated Learning (FL) based privacy preserving approach to facilitate collaborative FL among multiple model owners in the IoV. Our system model enables collaborative model training without compromising data privacy given that only the model parameters instead of the raw data are exchanged within the federation. However, there are two main challenges of incentive mismatches between workers and model owners, as well as among model owners. For the former, we leverage on the self-revealing mechanism in contract theory under information asymmetry. For the latter, we use the coalitional game theory approach that rewards model owners based on their marginal contributions. The numerical results validate the performance efficiency of our proposed hierarchical incentive mechanism design.

The increasing vehicles have brought convenience to people as well as many traffic problems. The Internet of Vehicles (IoV) is an extension of the intelligent transportation system based on the Internet of Things (IoT), which is the omnibearing network connection among “Vehicles, Loads, Clouds”. However, IoV also faces threats from various known and unknown security vulnerabilities. Traditional security defense methods can only deal with known attacks, while there is no effective way to deal with unknown attacks. In this paper, we show an IoV system deployed on a Mimic Common Operating Environment (MCOE). At the sensing layer, we introduce a lightweight cryptographic algorithm, LBlock, to encrypt the data collected by the hardware. Thus, we can prevent malicious tampering of information such as vehicle conditions. At the application layer, we firstly put the IoV system platform into MCOE to make it dynamic, heterogeneous and redundant. Extensive experiments prove that the sensing layer can encrypt data reliably and energy-efficiently. And we prove the feasibility and security of the Internet of Vehicles system platform on MCOE.

Considering the problem of network security under the background of big data, the clustering analysis algorithms can be utilized to improve the correctness of network intrusion detection models for security management. As a kind of iterative clustering analysis algorithm, K-means algorithm is not only simple but also efficient, so it is widely used. However, the traditional K-means algorithm cannot well solve the network security problem when facing big data due to its high complexity and limited processing ability. In this case, this paper proposes to optimize the traditional K-means algorithm based on the Spark platform and deploy the optimized clustering analysis algorithm in the distributed architecture, so as to improve the efficiency of clustering algorithm for network intrusion detection in big data environment. The experimental result shows that, compared with the traditional K-means algorithm, the efficiency of the optimized K-means algorithm using a Spark-based method is significantly improved in the running time.

A synthetic aperture radar (SAR) target detection method based on the fusion of multiscale superpixel segmentations is proposed in this paper. SAR images are segmented between land and sea firstly by using superpixel technology in different scales. Secondly, image segmentation results together with the constant false alarm rate (CFAR) detection result are coalesced. Finally, target detection is realized by fusing different scale results. The effectiveness of the proposed algorithm is tested on Sentinel-1A data.

With the advancement of communication technology, the interoperability of the power grid operation has improved significantly, but due to its dependence on the communication system, it is extremely vulnerable to network attacks. Among them, the false data injection attack utilizes the loophole of bad data detection in the system and attacks the state estimation system, resulting in frequent occurrence of abnormal data in the system, which brings great harm to the power grid. In view of the fact that false data injection attacks are easy to avoid traditional bad data detection methods, this paper analyzes the different situations of false data injection attacks based on the characteristics of the power grid. Firstly, it proposes to apply the distortion index method to false data injection attack detection. Experiments prove that the detection results are good and can be complementary to traditional detection methods. Then, combined with the traditional normalized residual method, this paper proposes the improved distortion index method based on the distortion index, which is good at detecting abnormal data. The use of improved distortion index method to detect false data injection attacks can make up for the defect of the lack of universality of traditional detection methods, and meet the requirements of anomaly detection efficiency. Finally, based on the MATLAB power simulation test system, experimental simulation is carried out to verify the effectiveness and universality of the proposed method for false data injection attack detection.

Similar to other digital assets, deep neural network (DNN) models could suffer from piracy threat initiated by insider and/or outsider adversaries due to their inherent commercial value. DNN watermarking is a promising technique to mitigate this threat to intellectual property. This work focuses on black-box DNN watermarking, with which an owner can only verify his ownership by issuing special trigger queries to a remote suspicious model. However, informed attackers, who are aware of the watermark and somehow obtain the triggers, could forge fake triggers to claim their ownerships since the poor robustness of triggers and the lack of correlation between the model and the owner identity. This consideration calls for new watermarking methods that can achieve better trade-off for addressing the discrepancy. In this paper, we exploit frequency domain image watermarking to generate triggers and build our DNN watermarking algorithm accordingly. Since watermarking in the frequency domain is high concealment and robust to signal processing operation, the proposed algorithm is superior to existing schemes in resisting fraudulent claim attack. Besides, extensive experimental results on 3 datasets and 8 neural networks demonstrate that the proposed DNN watermarking algorithm achieves similar performance on functionality metrics and better performance on security metrics when compared with existing algorithms.

Mobile banking apps, belonging to the most security-critical app category, render massive and dynamic transactions susceptible to security risks. Given huge potential financial loss caused by vulnerabilities, existing research lacks a comprehensive empirical study on the security risks of global banking apps to provide useful insights and improve the security of banking apps. Since data-related weaknesses in banking apps are critical and may directly cause serious financial loss, this paper first revisits the state-of-the-art available tools and finds that they have limited capability in identifying data-related security weaknesses of banking apps. To complement the capability of existing tools in data-related weakness detection, we propose a three-phase automated security risk assessment system, named Ausera, which leverages static program analysis techniques and sensitive keyword identification. By leveraging Ausera, we collect 2,157 weaknesses in 693 real-world banking apps across 83 countries, which we use as a basis to conduct a comprehensive empirical study from different aspects, such as global distribution and weakness evolution during version updates. We find that apps owned by subsidiary banks are always less secure than or equivalent to those owned by parent banks. In addition, we also track the patching of weaknesses and receive much positive feedback from banking entities so as to improve the security of banking apps in practice. We further find that weaknesses derived from outdated versions of banking apps or third-party libraries are highly prone to being exploited by attackers. To date, we highlight that 21 banks have confirmed the weaknesses we reported (including 126 weaknesses in total). We also exchange insights with 7 banks, such as HSBC in UK and OCBC in Singapore, via in-person or online meetings to help them improve their apps. We hope that the insights developed in this paper will inform the communities about the gaps among multiple stakeholders, including banks, academic researchers, and third-party security companies.

In this paper, the privacy preserving average consensus problem of multi-agent systems with strongly connected and weight balanced graph is considered. In most existing consensus algorithms, the agents need to exchange their state information, which leads to the disclosure of their initial states. This might be undesirable because agents' initial states may contain some important and sensitive information. To solve the problem, we propose a novel distributed algorithm, which can guarantee average consensus and meanwhile preserve the agents' privacy. This algorithm assigns some additive perturbation signals on the communication edges and these perturbations signals will be added to original true states for information exchanging. This ensures that direct disclosure of initial states can be avoided. Then a rigid analysis of our algorithm's privacy preserving performance is provided. For any individual agent in the network, we present a necessary and sufficient condition under which its privacy is preserved. The effectiveness of our algorithm is demonstrated by a numerical simulation.

As the hottest frontier technology in the field of artificial intelligence, machine learning is subverting various industries step by step. In the future, it will penetrate all aspects of our lives and become an indispensable technology around us. Among them, network security is an area where machine learning can show off its strengths. Among many network security problems, privacy protection is a more difficult problem, so it needs more introduction of new technologies, new methods and new ideas such as machine learning to help solve some problems. The research contents for this include four parts: an overview of machine learning, the significance of machine learning in network security, the application process of machine learning in network security research, and the application of machine learning in privacy protection. It focuses on the issues related to privacy protection and proposes to combine the most advanced matching algorithm in deep learning methods with information theory data protection technology, so as to introduce it into biometric authentication. While ensuring that the loss of matching accuracy is minimal, a high-standard privacy protection algorithm is concluded, which enables businesses, government entities, and end users to more widely accept privacy protection technology.

Here, we propose a simple design approach based on metal-masked titanium dioxide nanopillars, which can realize strong Mie resonance in metasurfaces and enables light confinement within itself over the range of visible wavelengths. By selecting the appropriate period and diameter of individual titanium dioxide nanopillars, the coincidence of resonance peak positions derived from excited electric and magnetic dipoles can be achived. And the optical properties in this design have been investigated with the Finite-Difference Time-Domain(FDTD) solutions.

Data races occur when two threads fail to use proper synchronization when accessing shared data. In kernel file systems, which are highly concurrent by design, data races are common mistakes and often wreak havoc on the users, causing inconsistent states or data losses. Prior fuzzing practices on file systems have been effective in uncovering hundreds of bugs, but they mostly focus on the sequential aspect of file system execution and do not comprehensively explore the concurrency dimension and hence, forgo the opportunity to catch data races.In this paper, we bring coverage-guided fuzzing to the concurrency dimension with three new constructs: 1) a new coverage tracking metric, alias coverage, specially designed to capture the exploration progress in the concurrency dimension; 2) an evolution algorithm for generating, mutating, and merging multi-threaded syscall sequences as inputs for concurrency fuzzing; and 3) a comprehensive lockset and happens-before modeling for kernel synchronization primitives for precise data race detection. These components are integrated into Krace, an end-to-end fuzzing framework that has discovered 23 data races in ext4, btrfs, and the VFS layer so far, and 9 are confirmed to be harmful.

Trust relationship prediction among people provides valuable supports for decision making, information dissemination, and product promotion in online social networks. Network embedding has achieved promising performance for link prediction by learning node representations that encode intrinsic network structures. However, most of the existing network embedding solutions cannot effectively capture the properties of a trust network that has directed edges and nodes with in/out links. Furthermore, there usually exist rich user attributes in trust networks, such as ratings, reviews, and the rated/reviewed items, which may exert significant impacts on the formation of trust relationships. It is still lacking a network embedding-based method that can adequately integrate these properties for trust prediction. In this work, we develop an AtNE-Trust model to address these issues. We firstly capture user embedding from both the trust network structures and user attributes. Then we design a deep multi-view representation learning module to further mine and fuse the obtained user embedding. Finally, a trust evaluation module is developed to predict the trust relationships between users. Representation learning and trust evaluation are optimized together to capture high-quality user embedding and make accurate predictions simultaneously. A set of experiments against the real-world datasets demonstrates the effectiveness of the proposed approach.

IoT devices provide a rich data source that is not available in the past, which is valuable for a wide range of intelligence applications, especially deep neural network (DNN) applications that are data-thirsty. An established DNN model provides useful analysis results that can improve the operation of IoT systems in turn. The progress in distributed/federated DNN training further unleashes the potential of integration of IoT and intelligence applications. When a large number of IoT devices are deployed in different physical locations, distributed training allows training modules to be deployed to multiple edge data centers that are close to the IoT devices to reduce the latency and movement of large amounts of data. In practice, these IoT devices and edge data centers are usually owned and managed by different parties, who do not fully trust each other or have conflicting interests. It is hard to coordinate them to provide end-to-end integrity protection of the DNN construction and application with classical security enhancement tools. For example, one party may share an incomplete data set with others, or contribute a modified sub DNN model to manipulate the aggregated model and affect the decision-making process. To mitigate this risk, we propose a novel blockchain based end-to-end integrity protection scheme for DNN applications integrated with an IoT system in the edge computing environment. The protection system leverages a set of cryptography primitives to build a blockchain adapted for edge computing that is scalable to handle a large number of IoT devices. The customized blockchain is integrated with a distributed/federated DNN to offer integrity and authenticity protection services.

With the introduction of new technologies such as cloud computing and big data, the security issues of industrial cyber-physical systems (ICPSs) have become more complicated. Meanwhile, a lot of current security research lacks adaptation to industrial system upgrades. In this paper, an edge-cloud synergy framework for security decision-making is proposed, which takes advantage of the huge convenience and advantages brought by cloud computing and edge computing, and can make security decisions on a global perspective. Under this framework, a combination of Bayesian network-based risk assessment and stochastic game model-based security decision-making is proposed to generate an optimal defense strategy to minimize system losses. This method trains models in the clouds and infers at the edge computing nodes to achieve rapid defense strategy generation. Finally, a case study on the hardware-in-the-loop simulation platform proves the feasibility of the approach.

Intelligenta transportation is an important part of urban development. The core of realizing intelligent transportation is to master the urban road condition. This system processes the video of dashcam based on the Panoptic Segmentation network and adds a tracking module based on the comparison of front and rear frames and KM algorithm. The system mainly includes the following parts: embedded device, Panoptic Feature Pyramid Network, cloud server and Web site.

Human action is naturally compositional: humans can easily recognize and perform actions with objects that are different from those used in training demonstrations. In this paper, we study the compositionality of action by looking into the dynamics of subject-object interactions. We propose a novel model which can explicitly reason about the geometric relations between constituent objects and an agent performing an action. To train our model, we collect dense object box annotations on the Something-Something dataset. We propose a novel compositional action recognition task where the training combinations of verbs and nouns do not overlap with the test set. The novel aspects of our model are applicable to activities with prominent object interaction dynamics and to objects which can be tracked using state-of-the-art approaches; for activities without clearly defined spatial object-agent interactions, we rely on baseline scene-level spatio-temporal representations. We show the effectiveness of our approach not only on the proposed compositional action recognition task but also in a few-shot compositional setting which requires the model to generalize across both object appearance and action category.

In order to improve the buffering performance of the data encrypted by CP-ABE (ciphertext policy attribute based encryption), this paper proposed a Markov prefetching model based on attribute classification. The prefetching model combines the access strategy of CP-ABE encrypted file, establishes the user relationship network according to the attribute value of the user, classifies the user by the modularity-based community partitioning algorithm, and establishes a Markov prefetching model based on attribute classification. In comparison with the traditional Markov prefetching model and the classification-based Markov prefetching model, the attribute-based Markov prefetching model is proposed in this paper has higher prefetch accuracy and coverage.

Energy Internet is a typical cyber-physical system (CPS), in which the disturbance on cyber part may result in the operation risks on the physical part. In order to perform CPS assessment and research the interactive influence between cyber part and physical part, an integrated energy internet CPS model which adopts information flow matrix, energy control flow matrix and information energy hybrid flow matrix is proposed in this paper. The proposed model has a higher computational efficacy compared with simulation based approaches. Then, based on the proposed model, the influence of cyber disturbances such as data dislocation, data delay and data error on the physical part are studied. Finally, a 3 MW PET based energy internet CPS is built using PSCAD/EMTDC software. The simulation results prove the validity of the proposed model and the correctness of the interactive influence analysis.

With the progressive development of web applications and the urgent requirement of web security, vulnerability scanner has been particularly emphasized, which is regarded as a fundamental component for web security assurance. Various scanners are developed with the intention of that discovering the possible vulnerabilities in advance to avoid malicious attacks. However, most of them only focus on the vulnerability detection with single target, which fail in satisfying the efficiency demand of users. In this paper, an effective web vulnerability scanner that integrates the information collection with the vulnerability detection is proposed to verify whether the target web application is vulnerable or not. The experimental results show that, by guiding the detection process with the useful collected information, our tool achieves great web vulnerability detection capability with a large scanning scope.

Ahstract-Vulnerability detection is an important topic of software engineering. To improve the effectiveness and efficiency of vulnerability detection, many traditional machine learning-based and deep learning-based vulnerability detection methods have been proposed. However, the impact of different factors on vulnerability detection is unknown. For example, classification models and vectorization methods can directly affect the detection results and code replacement can affect the features of vulnerability detection. We conduct a comparative study to evaluate the impact of different classification algorithms, vectorization methods and user-defined variables and functions name replacement. In this paper, we collected three different vulnerability code datasets. These datasets correspond to different types of vulnerabilities and have different proportions of source code. Besides, we extract and analyze the features of vulnerability code datasets to explain some experimental results. Our findings from the experimental results can be summarized as follows: (i) the performance of using deep learning is better than using traditional machine learning and BLSTM can achieve the best performance. (ii) CountVectorizer can improve the performance of traditional machine learning. (iii) Different vulnerability types and different code sources will generate different features. We use the Random Forest algorithm to generate the features of vulnerability code datasets. These generated features include system-related functions, syntax keywords, and user-defined names. (iv) Datasets without user-defined variables and functions name replacement will achieve better vulnerability detection results.

Unlike traditional processors, Internet of Things (IoT) devices are short of resources to incorporate mature protections (e.g. MMU, TrustZone) against modern control-flow attacks. Remote (control-flow) attestation is fast becoming a key instrument in securing such devices as it has proven the effectiveness on not only detecting runtime malware infestation of a remote device, but also saving the computing resources by moving the costly verification process away. However, few control-flow attestation schemes have been able to draw on any systematic research into the software specificity of bare-metal systems, which are widely deployed on resource-constrained IoT devices. To our knowledge, the unique design patterns of the system limit implementations of such expositions. In this paper, we present the design and proof-of-concept implementation of LAPE, a lightweight attestation of program execution scheme that enables detecting control-flow attacks for bare-metal systems without requiring hardware modification. With rudimentary memory protection support found in modern IoT-class microcontrollers, LAPE leverages software instrumentation to compartmentalize the firmware functions into several ”attestation compartments”. It then continuously tracks the control-flow events of each compartment and periodically reports them to the verifier. The PoC of the scheme is incorporated into an LLVM-based compiler to generate the LAPE-enabled firmware. By taking experiments with several real-world IoT firmware, the results show both the efficiency and practicality of LAPE.

Due to the mobility and openness of wireless body area networks (WBANs), the security of WBAN has been questioned by people. The patient's physiological information in WBAN is sensitive and confidential, which requires full consideration of user anonymity, untraceability, and data privacy protection in key agreement. Aiming at the shortcomings of Li et al.'s protocol in terms of anonymity and session unlinkability, forward/backward confidentiality, etc., a new anonymous mutual authentication and key agreement protocol was proposed on the basis of the protocol. This scheme only uses XOR and the one-way hash operations, which not only reduces communication consumption but also ensures security, and realizes a truly lightweight anonymous mutual authentication and key agreement protocol.

Anonymous communication networks (ACNs) are intended to protect the metadata during communication. As classic ACNs, onion mix-nets are famous for strong anonymity, in which the source defines a static path and wraps the message multi-times with the public keys of nodes on the path, through which the message is relayed to the destination. However, onion mix-nets lacks in resilience when the static on-path mixes fail. Mix failure easily results in message loss, communication failure, and even specific attacks. Therefore, it is desirable to achieve resilient routing in onion mix-nets, providing persistent routing capability even though node failure. The state-of-theart solutions mainly adopt mix groups and thus need to share secret keys among all the group members which may cause single point of failure. To address this problem, in this work we propose a hybrid routing approach, which embeds the onion mix-net with hop-by-hop routing to increase routing resilience. Furthermore, we propose the threshold hybrid routing to achieve better key management and avoid single point of failure. As for experimental evaluations, we conduct quantitative analysis of the resilience and realize a local T-hybrid routing prototype to test performance. The experimental results show that our proposed routing strategy increases routing resilience effectively, at the expense of acceptable latency.

We study the attribution problem for deep networks applied to perception tasks. For vision tasks, attribution techniques attribute the prediction of a network to the pixels of the input image. We propose a new technique called Blur Integrated Gradients (Blur IG). This technique has several advantages over other methods. First, it can tell at what scale a network recognizes an object. It produces scores in the scale/frequency dimension, that we find captures interesting phenomena. Second, it satisfies the scale-space axioms, which imply that it employs perturbations that are free of artifact. We therefore produce explanations that are cleaner and consistent with the operation of deep networks. Third, it eliminates the need for baseline parameter for Integrated Gradients for perception tasks. This is desirable because the choice of baseline has a significant effect on the explanations. We compare the proposed technique against previous techniques and demonstrate application on three tasks: ImageNet object recognition, Diabetic Retinopathy prediction, and AudioSet audio event identification. Code and examples are at https://github.com/PAIR-code/saliency.

With the deployment of artificial intelligent (AI) algorithms in a large variety of applications, there creates an increasing need for high-performance computing capabilities. As a result, different hardware platforms have been utilized for acceleration purposes. Among these hardware-based accelerators, the field-programmable gate arrays (FPGAs) have gained a lot of attention due to their re-programmable characteristics, which provide customized control logic and computing operators. For example, FPGAs have recently been adopted for on-demand cloud services by the leading cloud providers like Amazon and Microsoft, providing acceleration for various compute-intensive tasks. While the co-residency of multiple tenants on a cloud FPGA chip increases the efficiency of resource utilization, it also creates unique attack surfaces that are under-explored. In this paper, we exploit the vulnerability associated with the shared power distribution network on cloud FPGAs. We present a stealthy power attack that can be remotely launched by a malicious tenant, shutting down the entire chip and resulting in denial-of-service for other co-located benign tenants. Specifically, we propose stealthy-shutdown: a well-timed power attack that can be implemented in two steps: (1) an attacker monitors the realtime FPGA power-consumption detected by ring-oscillator-based voltage sensors, and (2) when capturing high power-consuming moments, i.e., the power consumption by other tenants is above a certain threshold, she/he injects a well-timed power load to shut down the FPGA system. Note that in the proposed attack strategy, the power load injected by the attacker only accounts for a small portion of the overall power consumption; therefore, such attack strategy remains stealthy to the cloud FPGA operator. We successfully implement and validate the proposed attack on three FPGA evaluation kits with running real-world applications. The proposed attack results in a stealthy-shutdown, demonstrating severe security concerns of co-tenancy on cloud FPGAs. We also offer two countermeasures that can mitigate such power attacks.