Biblio

The complexity and scale of modern software programs often lead to overlooked programming errors and security vulnerabilities. Developers often rely on automatic tools, like static analysis tools, to look for bugs and vulnerabilities. Static analysis tools are widely used because they can understand nontrivial program behaviors, scale to millions of lines of code, and detect subtle bugs. However, they are known to generate an excess of false alarms which hinder their utilization as it is counterproductive for developers to go through a long list of reported issues, only to find a few true positives. One of the ways proposed to suppress false positives is to use machine learning to identify them. However, training machine learning models requires good quality labeled datasets. For this purpose, we developed D2A [3], a differential analysis based approach that uses the commit history of a code repository to create a labeled dataset of Infer [2] static analysis output.

Flexibility and speed in the development of new industrial machines are essential factors for the success of capital goods industries. When assembling a printed circuit board (PCB), since all the components are surface mounted devices (SMD), the whole process is automatic. However, in many PCBs, it is necessary to place components that are not SMDs, called pin through hole components (PTH), having to be inserted manually, which leads to delays in the production line. This work proposes and validates a prototype work cell based on a collaborative robot and vision systems whose objective is to insert these components in a completely autonomous or semi-autonomous way. Different tests were made to validate this work cell, showing the correct implementation and the possibility of replacing the human worker on this PCB assembly task.

We propose new, more efficient targeted whitebox attacks against deep neural networks. Our attacks better align with the attacker’s goal: (1) tricking a model to assign higher probability to the target class than to any other class, while (2) staying within an -distance of the attacked input. First, we demonstrate a loss function that explicitly encodes (1) and show that Auto-PGD finds more attacks with it. Second, we propose a new attack method, Constrained Gradient Descent (CGD), using a refinement of our loss function that captures both (1) and (2). CGD seeks to satisfy both attacker objectives—misclassification and bounded `p-norm—in a principled manner, as part of the optimization, instead of via ad hoc postprocessing techniques (e.g., projection or clipping). We show that CGD is more successful on CIFAR10 (0.9–4.2%) and ImageNet (8.6–13.6%) than state-of-the-art attacks while consuming less time (11.4–18.8%). Statistical tests confirm that our attack outperforms others against leading defenses on different datasets and values of .

Many self-adaptive systems benefit from human involvement and oversight, where a human operator can provide expertise not available to the system and detect problems that the system is unaware of. One way of achieving this synergy is by placing the human operator on the loop—i.e., providing supervisory oversight and intervening in the case of questionable adaptation decisions. To make such interaction effective, an explanation can play an important role in allowing the human operator to understand why the system is making certain decisions and improve the level of knowledge that the operator has about the system. This, in turn, may improve the operator’s capability to intervene and, if necessary, override the decisions being made by the system. However, explanations may incur costs, in terms of delay in actions and the possibility that a human may make a bad judgment. Hence, it is not always obvious whether an explanation will improve overall utility and, if so, then what kind of explanation should be provided to the operator. In this work, we define a formal framework for reasoning about explanations of adaptive system behaviors and the conditions under which they are warranted. Specifically, we characterize explanations in terms of explanation content, effect, and cost. We then present a dynamic system adaptation approach that leverages a probabilistic reasoning technique to determine when an explanation should be used to improve overall system utility. We evaluate our explanation framework in the context of a realistic industrial control system with adaptive behaviors.

This study addresses the coordination issue of multi-agent systems under complicated actuator faults and cyber attacks. Distributed fault-tolerant design is developed with the estimated and output neighboring information in decentralized estimation observer. Criteria of reaching the exponential coordination of multi-agent systems with cyber attacks is obtained with average dwelling time and chattering bound method. Simulations validate the efficiency of the anti-attack fault-tolerant design.

Cloud data integrity verification was an important means to ensure data security. We used public key infrastructure (PKI) to manage user keys in Traditional way, but there were problems of certificate verification and high cost of key management. In this paper, RSA signature was used to construct a new identity-based cloud audit protocol, which solved the previous problems caused by PKI and supported forward security, and reduced the loss caused by key exposure. Through security analysis, the design scheme could effectively resist forgery attack and support forward security.

In healthcare 4.0 ecosystems, authentication of healthcare information allows health stakeholders to be assured that data is originated from correct source. Recently, biometric based authentication is a preferred choice, but as the templates are stored on central servers, there are high chances of copying and generating fake biometrics. An adversary can forge the biometric pattern, and gain access to critical health systems. Thus, to address the limitation, the paper proposes a scheme, PHBio, where an encryption-based biometric system is designed prior before storing the template to the server. Once a user provides his biometrics, the authentication process does not decrypt the data, rather uses a homomorphic-enabled Paillier cryptosystem. The scheme presents the encryption and the comparison part which is based on euclidean distance (EUD) strategy between the user input and the stored template on the server. We consider the minimum distance, and compare the same with a predefined threshold distance value to confirm a biometric match, and authenticate the user. The scheme is compared against parameters like accuracy, false rejection rates (FARs), and execution time. The proposed results indicate the validity of the scheme in real-time health setups.

The cloud provides storage for users to share their files in the cloud. Nowadays some shared data auditing schemes are proposed for protecting data integrity. However, preserving the identity privacy of group users and secure user revocation usually result in high computational overhead. Then a shared data auditing scheme supporting identity privacy preserving is proposed that enables users to be effectively revoked. To preserve identity privacy during the audit process, we develop an efficient authenticator generation mechanism that enables public auditing. Our solution supports efficient user revocation, where the authenticator of the revoked user does not need to be regenerated and integrity checking can be performed appropriately. At the same time, the group manager maintains two tables to ensure user traceability. When the user updates data, two tables are modified and updated by the group manager promptly. It shows that our scheme is secure by security analysis. Moreover, concrete experiments prove the performance of the system.

The security control problem of cyber-physical system (CPS) under actuator attacks is studied in the paper. Considering the strict-feedback cyber-physical systems with external disturbance, a security control scheme is proposed by combining backstepping method and super-twisting sliding mode technology when the transmission control input signal of network layer is under false data injection(FDI) attack. Firstly, the unknown nonlinear function of the CPS is identified by Radial Basis Function Neural Network. Secondly, the backstepping method and super-twisting sliding mode algorithm are combined to eliminate the influence of actuator attack and ensure the robustness of the control system. Then, by Lyapunov stability theory, it is proved that the proposed control scheme can ensure that all signals in the closed-loop system are semi-global and ultimately uniformly bounded. Finally, the effectiveness of the proposed control scheme is verified by the inverted pendulum simulation.

In the era of big data, information security is faced with many threats, among which memory data security of intelligent devices is an important link. Attackers can read the memory of specific devices, and then steal secrets, alter data, affect the operation of intelligent devices, and bring security threats. Data security is usually protected by encryption algorithm for device ciphertext conversion, so the safe generation and use of key becomes particularly important. In this paper, based on the advantages of SRAM PUF, such as real-time generation, power failure and disappearance, safety and reliability, a key generation unit is designed and implemented. BCH code is used as the error correction algorithm to generate 128-bit stable key, which provides a guarantee for the safe storage of intelligent devices.

Intrusion detection systems (IDSs) are widely deployed in the industrial control systems to protect network security. IDSs typically generate a huge number of alerts, which are time-consuming for system operators to process. Most of the alerts are individually insignificant false alarms. However, it is not the best solution to discard these alerts, as they can still provide useful information about network situation. Based on the study of characteristics of alerts in the industrial control systems, we adopt an enhanced method of exponentially weighted moving average (EWMA) control charts to help operators in processing alerts. We classify all detection signatures as regular and irregular according to their frequencies, set multiple control limits to detect anomalies, and monitor regular signatures for network security situational awareness. Extensive experiments have been performed using real-world alert data. Simulation results demonstrate that the proposed enhanced EWMA method can greatly reduce the volume of alerts to be processed while reserving significant abnormal information.

Swarm learning (SL) is an emerging promising decentralized machine learning paradigm and has achieved high performance in clinical applications. SL solves the problem of a central structure in federated learning by combining edge computing and blockchain-based peer-to-peer network. While there are promising results in the assumption of the independent and identically distributed (IID) data across participants, SL suffers from performance degradation as the degree of the non-IID data increases. To address this problem, we propose a generative augmentation framework in swarm learning called SL-GAN, which augments the non-IID data by generating the synthetic data from participants. SL-GAN trains generators and discriminators locally, and periodically aggregation via a randomly elected coordinator in SL network. Under the standard assumptions, we theoretically prove the convergence of SL-GAN using stochastic approximations. Experimental results demonstrate that SL-GAN outperforms state-of-art methods on three real world clinical datasets including Tuberculosis, Leukemia, COVID-19.

Smart grids are envisioned as the next-generation electricity grids. The data measured from the smart grid is very sensitive. It is thus highly necessary to adopt data access control in smart grids to guarantee the security and privacy of the measured data. Due to its flexibility and scalability, attribute-based encryption (ABE) is widely utilized to realize data access control in smart grids. However, most existing ABE solutions impose a heavy decryption overhead on their users. To this end, we propose a lightweight attribute-based encryption scheme for data access control in smart grids by adopting the idea of computation outsourcing. Under our proposed scheme, users can outsource a large amount of computation to a server during the decryption phase while still guaranteeing the security and privacy of the data. Theoretical analysis and experimental evaluation demonstrate that our scheme outperforms the existing schemes by achieving a very low decryption cost.

Password-based authentication system has been praised for its user-friendly, cost-effective, and easily deployable features. It is arguably the most commonly used security mechanism for various resources, services, and applications. On the other hand, it has well-known security flaws, including vulnerability to guessing attacks. Present state-of-the-art approaches have high overheads, as well as difficulties and unreliability during training, resulting in a poor user experience and a high false positive rate. As a result, a lightweight authentication compromise detection model that can make accurate detection with a low false positive rate is required.In this paper we propose – LOG-OFF – a behavior-based authentication compromise detection model. LOG-OFF is a lightweight model that can be deployed efficiently in practice because it does not include a labeled dataset. Based on the assumption that the behavioral pattern of a specific user does not suddenly change, we study the real-world authentication traffic data. The dataset contains more than 4 million records. We use two features to model the user behaviors, i.e., consecutive failures and login time, and develop a novel approach. LOG-OFF learns from the historical user behaviors to construct user profiles and makes probabilistic predictions of future login attempts for authentication compromise detection. LOG-OFF has a low false positive rate and latency, making it suitable for real-world deployment. In addition, it can also evolve with time and make more accurate detection as more data is being collected.

In the PKI-CA system with a traditional trust model based on trust chain and centralized private key management, there are some problems with issuing certificates illegally, denying issued certificates, tampering with issuance log, and leaking certificate private key due to the excessive power of a single CA. A novel distributed CA system based on blockchain was constructed to solve the problems. The system applied blockchain and smart contract to coordinate the certificate issuing process, and stored the issuing process logs and information used to verify certificates on the blockchain. It guaranteed the non-tamperability and non-repudiation of logs and information. Aiming at the disadvantage of easy leakage of private keys in centralized management mode, the system used the homomorphism of elliptic encryption algorithm, CPK and transformation matrix to generate and store user private keys safely and distributively. Experimental analysis showed that the system can not only overcome the drawbacks of the traditional PKI-CA system, but also issue certificates quickly and save as much storage as possible to store certificate private keys.

This paper focuses on the system on wireless sensor networks. The system is linear and the time of the system is discrete as well as variable, which named discrete-time linear time-varying systems (DLTVS). DLTVS are vulnerable to network attacks when exchanging information between sensors in the network, as well as putting their security at risk. A DLTVS with privacy-preserving is designed for this purpose. A set-membership estimator is designed by adding privacy noise obeying the Laplace distribution to state at the initial moment. Simultaneously, the differential privacy of the system is analyzed. On this basis, the real state of the system and the existence form of the estimator for the desired distribution are analyzed. Finally, simulation examples are given, which prove that the model after adding differential privacy can obtain accurate estimates and ensure the security of the system state.

Code-graph based software defect prediction methods have become a research focus in SDP field. Among them, Code Property Graph is used as a form of data representation for code defects due to its ability to characterize the structural features and dependencies of defect codes. However, since the coarse granularity of Code Property Graph, redundant information which is not related to defects often attached to the characterization of software defects. Thus, it is a problem to be solved in how to locate software defects at a finer granularity in Code Property Graph. Static analysis is a technique for identifying software defects using set defect rules, and there are many proven static analysis tools in the industry. In this paper, we propose a method for locating specific types of defects in the Code Property Graph based on the result of static analysis tool. Experiments show that the location method based on static analysis results can effectively predict the location of specific defect types in real software program.

With the increasing complexity of the driving environment, more and more attention has been paid to the research on improving the intelligentization of traffic control. Among them, the digital twin-based internet of vehicle can establish a mirror system on the cloud to improve the efficiency of communication between vehicles, provide warning and safety instructions for drivers, avoid driving potential dangers. To ensure the security and effectiveness of data sharing in traffic control, this paper proposes a secure and privacy-preserving scheme for digital twin-based traffic control. Specifically, in the data uploading phase, we employ a group signature with a time-bound keys technique to realize data source authentication with efficient members revocation and privacy protection, which can ensure that data can be securely stored on cloud service providers after it synchronizes to its twin. In the data sharing stage, we employ the secure and efficient attribute-based access control technique to provide flexible and efficient data sharing, in which the parameters of a specific sub-policy can be stored during the first decryption and reused in subsequent data access containing the same sub-policy, thus reducing the computing complexity. Finally, we analyze the security and efficiency of the scheme theoretically.

Access control includes authorization of security administrators and access of users. Aiming at the problems of log information storage difficulty and easy tampering faced by auditing and traceability forensics of authorization and access in cross-domain scenarios, we propose an access control auditing and traceability forensics method based on Blockchain, whose core is Ethereum Blockchain and IPFS interstellar mail system, and its main function is to store access control log information and trace forensics. Due to the technical characteristics of blockchain, such as openness, transparency and collective maintenance, the log information metadata storage based on Blockchain meets the requirements of distribution and trustworthiness, and the exit of any node will not affect the operation of the whole system. At the same time, by storing log information in the blockchain structure and using mapping, it is easy to locate suspicious authorization or judgment that lead to permission leakage, so that security administrators can quickly grasp the causes of permission leakage. Using this distributed storage structure for security audit has stronger anti-attack and anti-risk.

Explainable Artificial Intelligence (XAI) research focuses on effective explanation techniques to understand and build AI models with trust, reliability, safety, and fairness. Feature importance explanation summarizes feature contributions for end-users to make model decisions. However, XAI methods may produce varied summaries that lead to further analysis to evaluate the consistency across multiple XAI methods on the same model and data set. This paper defines metrics to measure the consistency of feature contribution explanation summaries under feature importance order and saliency map. Driven by these consistency metrics, we develop an XAI process oriented on the XAI criterion of feature importance, which performs a systematical selection of XAI techniques and evaluation of explanation consistency. We demonstrate the process development involving twelve XAI methods on three topics, including a search ranking system, code vulnerability detection and image classification. Our contribution is a practical and systematic process with defined consistency metrics to produce rigorous feature contribution explanations.

As a mature and open mobile operating system, Android runs on many IoT devices, which has led to Android-based IoT devices have become a hotbed of malware. Existing static detection methods for malware using artificial intelligence algorithms focus only on the java code layer when extracting API features, however there is a lot of malicious behavior involving native layer code. Thus, to make up for the neglect of the native code layer, we propose a heterogeneous information network-based Android malware detection method with cross-layer features. We first translate the semantic information of apps and API calls into the form of meta-paths, and construct the adjacency of apps based on API calls, then combine information from different meta-paths using multi-core learning. We implemented our method on the dataset from VirusShare and AndroZoo, and the experimental results show that the accuracy of our method is 93.4%, which is at least 2% higher than other related methods using heterogeneous information networks for malware detection.

To reduce the false negative rate in power data anomaly detection, enhance the overall detection accuracy and reliability, and create a more stable data detection environment, this paper designs a power big data anomaly detection method based on improved support vector machine technology. The abnormal features are extracted in advance, combined with the changes of power data, the multi-target anomaly detection nodes are laid, and on this basis, the improved support vector machine anomaly detection model is constructed. The anomaly detection is realized by combining the normalization processing of the equivalent vector. The final test results show that compared with the traditional clustering algorithm big data anomaly detection test group and the traditional multi-domain feature extraction big data anomaly detection test group, the final false negative rate of the improved support vector machine big data exception detection test group designed in this paper is only 2.04, which shows that the effect of the anomaly detection method is better. It is more accurate and reliable for testing in a complex power environment and has practical application value.

In the traditional Internet of Vehicles, communication data is easily tampered with and easily leaked. In order to improve the trust evaluation mechanism of the Internet of Vehicles and establish a trust relationship between vehicles, a blockchain-based Internet of Vehicles trust evaluation (BBTE) scheme is proposed. First, the scheme uses the roadside unit RSU to calculate the trust value of vehicle nodes and maintain the generation, verification and storage of blocks, so as to realize distributed data storage and ensure that data cannot be tampered with. Secondly, an efficient trust evaluation method is designed. The method integrates four trust decision factors: initial trust, historical experience trust, recommendation trust and RSU observation trust to obtain the overall trust value of vehicle nodes. In addition, in the process of constructing the recommendation trust method, the recommendation trust is divided into three categories according to the interaction between the recommended vehicle node and the communicator, use CRITIC to obtain the optimal weights of three recommended trusts, and use CRITIC to obtain the optimal weights of four trust decision-making factors to obtain the final trust value. Finally, the NS3 simulation platform is used to verify the security and accuracy of the trust evaluation method, and to improve the identification accuracy and detection rate of malicious vehicle nodes. The experimental analysis shows that the scheme can effectively deal with the gray hole attack, slander attack and collusion attack of other vehicle nodes, improve the security of vehicle node communication interaction, and provide technical support for the basic application of Internet of Vehicles security.

Document scanning aims to transfer the captured photographs documents into scanned document files. However, current methods based on traditional or key point detection have the problem of low detection accuracy. In this paper, we were the first to propose a document processing system based on semantic segmentation. Our system uses OCRNet to segment documents. Then, perspective transformation and other post-processing algorithms are used to obtain well-scanned documents based on the segmentation result. Meanwhile, we optimized OCRNet's loss function and reached 97.25 MIoU on the test dataset.

Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices corresponding to polyhedra and edges corresponding to polyhedra sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. When an image passes through a network containing ReLU nodes, the firing or non-firing at a node can be encoded as a bit (1 for ReLU activation, 0 for ReLU non-activation). The sequence of all bit activations identifies the image with a bit vector, which identifies it with a polyhedron in the decomposition and, in turn, identifies it with a vertex in the dual graph. We identify ReLU bits that are discriminators between non-adversarial and adversarial images and examine how well collections of these discriminators can ensemble vote to build an adversarial image detector. Specifically, we examine the similarities and differences of ReLU bit vectors for adversarial images, and their non-adversarial counterparts, using a pre-trained ResNet-50 architecture. While this paper focuses on adversarial digital images, ResNet-50 architecture, and the ReLU activation function, our methods extend to other network architectures, activation functions, and types of datasets.