Vehicle digital forensics (VDF) has attracted considerable attention within the Internet of Vehicles (IoV) amidst the rising incidence of traffic accidents. Ensuring the authenticity and integrity of evidence is crucial for vehicular investigations. However, attackers may tamper with vehicle data, undermining the credibility of digital forensics. To mitigate this issue, existing work has explored blockchain and encryption technologies to protect forensic information. However, two significant challenges remain. On one hand, due to the lightweight nature of blockchain, storing all data entirely on the blockchain can lead to data loss. On the other hand, multi-party blockchain forensic systems may be vulnerable to attacks on their system kernels, which could result in the leakage or tampering of sensitive data. In this paper, we propose PSVDF, a comprehensive framework for protecting and securing vehicle digital forensics. This framework effectively prevents data tampering by attackers and protects the privacy of individuals involved in accidents. We initially developed a cross-platform secure space with same-layer address space isolation to protect container memory data from tampering by untrusted host operating system that may store forensic information. Subsequently, we adopted an access control strategy based on view encryption to achieve collaborative storage between on-chain and off-chain systems. This not only reduces the load pressure on the blockchain system but also prevents privacy breaches caused by unauthorized access. Finally, we adopted the blockchain system as the foundational architecture to support our proposed framework. Both security analysis and experimental results demonstrate the feasibility and practicality of our solution.

Image-guided percutaneous needle puncture is a critical yet challenging clinical procedure, constrained by the high cognitive demand of mental model construction and manipulation of 3D anatomy via scrolling through 2D cross-sectional images. While virtual reality (VR) simulators provide a risk-free training platform, many focus on simulation fidelity but lack structured, self-directed learning frameworks. In this paper, we present PunctVR, a VR system that incorporates the instructional principles of scaffolding. PunctVR features a training mode employing a phased subgoal workflow and instructional guidance scaffolding, and an assessment-only test mode where both the workflow and enhanced 3D visualization are removed. We conducted a between-subject experiment with 16 physicians, comparing training using a baseline multiplanar reconstruction (MPR) view with a combined MPR + 3D visualization across two difficulty levels. Our test mode results indicate that all trainees significantly improved their performance after training. Furthermore, those who trained with the integrated 3D visualization achieved a greater reduction in puncture time in both easy and hard cases. These findings suggest that PunctVR effectively enhances procedural efficiency in simulated needle puncture training and provides important insights into how learning scaffolding can accelerate skill acquisition and retention for image-guided interventions.

Conditional dichotomy, the contrast between two outputs conditioned on the same context, is vital for applications such as debate, defeasible natural language inference, and causal reasoning.Existing methods that rely on semantic similarity often fail to capture the nuanced oppositional dynamics essential for these applications.Motivated by these limitations, we introduce a novel task, Conditional Dichotomy Quantification (ConDQ), which formalizes the direct measurement of conditional dichotomy and provides carefully constructed datasets covering debate, defeasible natural language inference, and causal reasoning scenarios.To address this task, we develop the Dichotomy-oriented Geometric Embedding (DoGE) framework, which leverages complex-valued embeddings and a dichotomous objective to model and quantify these oppositional relationships effectively.Extensive experiments validate the effectiveness and versatility of DoGE, demonstrating its potential in understanding and quantifying conditional dichotomy across diverse NLP applications.Our code and datasets are available at https://github.com/cui-shaobo/ conditional-dichotomy-quantification.

The quality of a seismic section is typically determined by the effectiveness of the frequency band: low-frequency information is advantageous for improving the quality of deep imaging, while high-frequency information helps to enhance resolution. Compressive sensing (CS) has the potential for precise spread extension. However, during the spread spectrum extension, a low signal-to-noise ratio (SNR) may lead to frequency anomalies, compensation artifacts, and issues caused by noise. In this article, based on the theory of CS, we derive a formula for full-frequency compensation with a shearlet denoising constraint. We analyze the effectiveness and feasibility of this method. Compared to other mathematical transforms, shearlet exhibits superior denoising capabilities and effective signal protection. In addition, by replacing the identity matrix in the denoising constraint with a sampling matrix, it can accurately reconstruct missing data, even when dealing with discontinuous data. To improve the accuracy and effectiveness of compensation, we perform autocorrelation calculations on the data to extend the wavelet for frequency compensation. We apply the proposed method to various field data, including thin layers, low SNR regions, missing data, and gas-bearing areas. Examples demonstrate the effectiveness and applicability of the proposed method.

Sign prediction in signed social networks is a new research direction in the field of social relation mining, which reveals underlying links between users. Traditional sign prediction research focuses on the prediction of positive signs and neglects the mining of potential implicit links, and there is little research on negative sign prediction. To address these problems, we propose a two-stage model that uses implicit link detection and link sign prediction. First, we use the preference attachment closeness degree (PACD) to predict possible implicit links by adding a measure of relationship closeness to the traditional link prediction algorithm (PA). Next, we propose a negative link sign prediction (Ne-LP) method to predict relation types through multidimensional negative sign-related features, including those of nodes, user similarity, and structural balance, and merge them by a logistic regression model. Finally, we evaluate PACD and Ne-LP through extensive experiments on three real-world social network datasets, whose results demonstrate that the method can effectively mine implicit relations and accurately predict negative links.

The HostOS or Hypervisor constitutes the most important cornerstone of today's commercial cloud environment security. Unfortunately, the HostOS/Hypervisor, especially the QEMU-KVM architecture, is not immune to all vulnerabilities and exploitations. Recently, researchers have put forward lots of schemes to protect Virtual Machines under the compromised HostOS/Hypervisor. However, some of these schemes rely on special hardware facilities, while other (e.g., Nested Virtualization schemes) require large modification to current commercial cloud architecture. In this paper, we present a novel scheme, named HyperPS, to implement virtual machine protection under the compromised HostOS/Hypervisor. The key idea of HyperPS is to deprive the HostOS/Hypervisor of the privileges of managing the physical memory into an isolated and trusted execution environment. HyperPS does not rely customized hardware or extra processor privilege. HyperPS shares the same privilege with the HostOS. We have implemented a fully functional prototype based on the KVM in Intel x86_64 architecture. Experiment results show that HyperPS has achieved an acceptable trade-off between security and performance.

This paper proposes an energy-efficient intelligent pulmonary auscultation system for post COVID-19 era wearable monitoring. This system consists of a tightly coupled two-stage hybrid neural network (TC-TSHNN) model and a corresponding multi-task training paradigm to improve prediction accuracy and generalization ability based on the fact that the number of COVID-19 patients is far less than that of normal people. At the first stage, two-category coarse classification is performed to identify normal and abnormal lung sounds. If the lung sound is abnormal, the second stage would be triggered to perform a four-category fine-grained classification. Besides, discrete wavelet transform is utilized for feature extraction, denoising and data reduction. In addition, advanced lightweight convolutional neural networks are used to reduce the model’s computation and improve the model’s performance. The hybrid network model can achieve 92% computation reduction and energy saving compared with a direct four-category classification when the input lung sound is normal, which is the majority of cases. Experiment results with inter-patient classification on the COVID-19 lung sound dataset from Tongji Hospital in Wuhan City and the ICBHI’17 dataset show that the proposed TC-TSHNN model can significantly reduce power consumption while maintaining competitive performance against the state-of-the-art work.

The large body of kernel code provides broad attack surfaces to exploitable bugs or misconfigurations. Current mitigations are difficult to be integrated together or have a non-trivial performance or code size impact. Thus, systematical protection for the kernel is of critical importance and is required. In this paper, we propose a kernel runtime security architecture, called HyperKRP, to provide systematical protection for kernel code, critical kernel data, and efficient kernel page tables. We have implemented a fully working prototype for a recent Linux kernel running on the Intel x86 processor. Our prototype is compromised of three protection engines based on a small size hypervisor. The evaluation shows that HyperKRP effectively ensures kernel runtime security with acceptable overhead.

This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks. Typical DNN classifiers encode the input image into a compressed latent representation more suitable for inference.This information bottleneck makes a trade-off between the image-specific structure and class-specific information in an image. By reinforcing the former while maintaining the latter, any redundant information, be it adversarial or not, should be removed from the latent representation. Hence, this paper proposes to jointly train an auto-encoder (AE) sharing the same encoding weights with the visual classifier. In order to reinforce the information bottleneck,we introduce the multi-scale low-pass objective and multi-scale high-frequency communication for better frequency steering in the network. Unlike existing approaches, our scheme is the first reforming defense per se which keeps the classifier structure untouched without appending any pre-processing head and is trained with clean images only. Extensive experiments on MNIST, CIFAR-10 and ImageNet demonstrate the strong defense of our method againstvarious adversarial attacks.

Environmental trace gas monitoring instrument (EMI) onboard GaoFen-5 was launched in May 2018 and has successfully operated on-orbit for more than a year. EMI contains four grating spectrometers, covering wavelengths in the range 240–710 nm with a spectral resolution of 0.3–0.5 nm, and enables one-day global coverage. For EMI on-orbit calibration, two onboard solar diffusers (SD), one surface reflectance aluminum diffuser, and one quartz volume diffuser (QVD) are used to measure solar spectra. The solar spectra are used to perform accurate spectral and radiometric calibrations. EMI on-orbit spectral calibration contains wavelength calibration and instrument spectral response function (ISRF), both of which are the key quantities in trace gas retrievals based on differential optical absorption spectroscopy (DOAS) analysis. The wavelength calibration is performed using the Fraunhofer lines in the solar spectrum, and the ISRF parameters are obtained by fitting high-resolution and EMI-measured solar spectra. Based on the known solar irradiation and characteristic of SD, SD radiance can be calculated and is used for EMI on-orbit radiometric calibration. The radiometric calibration also determines the absolute Earth reflectance spectra that are used as inputs for atmospheric retrieval algorithms. For EMI on-orbit radiometric monitoring, aluminum diffuser is used as reference SD to monitor QVD degradation. An internal white light source is used to detect pixel performance and monitor radiometric throughput.

Low-level languages like C/C++ are widely used in various applications for their performance and flexibility. Unfortunately, these languages are prone to memory corruption vulnerabilities, leading to control-flow hijacking attacks. Control flow integrity (CFI) is a general principle to enforce run-time control flow of a program to a pre-computed control-flow graph (CFG). While the traditional context-insensitive CFI falls short in protecting critical control transfers, recent context-sensitive CFI research shows promising improvements but has various limitations. We present Control Flow Integrity with Look Back (CFI-LB), a call-site sensitive CFI in which a conventional source-target control transfer is strengthened by a look back into its call-sites (return addresses). CFI-LB features the adaptive call-site sensitivity in which each indirect call has its own level of sensitivity and the multi-scope CFG to improve the security even if a precise context-sensitive static CFG is not available, especially for large programs such as GCC and NGINX. One of the CFGs is constructed by our localized concolic execution, which significantly extends the dynamic CFG with very low false positives. In addition, CFI-LB is the first CFI system explicitly designed to protect its reference monitors from race conditions. We have built a prototype of CFI-LB. The evaluation with SPEC CPU2006 benchmarks and NGINX indicates that CFI-LB has a low-performance overhead (less than 5% on average for the full protection) while increasing the security.

This paper proposes a new diffuse self-organizing map (DSOM), which is a competitive self-organizing neural network that can forms a topological map of the input vector space in a circle-shaped region. Active and inactive neurons are introduced to restrict the range of competition and the size of the final map. Lateral conduction is also introduced to calculate the learning radius and learning rate. DSOM learns in a uniform manner and is capable to learn new classes either within or after its learning stage.