Search

Controller area network (CAN) is the most commonly used bus technology for In-vehicle network and uses multicast communication without corresponding security measures. Therefore, the message data field is vulnerable to tampering and other attacks. Recent machine learning-based intrusion detection methods for CAN bus messages only use the information contained in the message data field and do not take into account the contribution made by the neighboring information of CAN bus messages. In addition, previous models considered the data domain information of CAN bus messages as separate features and did not consider the unique weight of each feature, as well as the second-order interaction information between features. Therefore, we propose a novel intrusion detection model, The Hybrid Similar Neighborhood Robust Factorization Machine Model (HSNRFM), for detecting anomalies in CAN bus messages to address the shortcomings and problems of the previous models. To be able to incorporate the contribution of similar neighborhood information and learn the unique weight parameters of each feature in the model decision process, as well as additional second-order interaction information between features, the HSNRFM model solves the above problem using a similarity calculation method and a factorization machine model. Comprehensive experimental results are compared on real vehicle datasets. The HSNRFM model has AUC values of 0.9216 and 0.901 and AUPR values of 0.9194 and 0.9018 on two real datasets, respectively. And the results show that our proposed HSNRFM model has excellent detection efficiency for intrusion detection of CAN bus messages. [ABSTRACT FROM AUTHOR]

Building on the TMT behavioral integration of upper echelon theory, this study explores whether the stability of top management team (TMT) affects sustainable corporate social responsible activities (CSR). We also examine how the TMT stability-sustainable CSR relationship is moderated by CEO power. Analyzing a dataset of publicly listed firms in China for the period of 2009–2017, we provide evidence that a relatively stable TMT engages in sustainable CSR. This finding supports the argument that a stable TMT focuses on long-term sustainable development. Moreover, the positive effect of TMT stability on sustainable CSR is pronounced only for firms with weak CEO power. Further analysis shows that a positive association between TMT stability and sustainable CSR occurs for firms in CSR-sensitive industries and in an environment with low economic uncertainty. We then confirm that TMT stability positively affects sustainable CSR by improving team cohesion, which in turn contributes to higher firm performance and lower operational risk. [ABSTRACT FROM AUTHOR]

Attacks launched from the inside of the cloud are threats not only to the cloud users but also to the cloud infrastructures. Although with trusted computing the cloud service providers can guarantee the trust and security of the cloud environment for the users, the trustworthiness of users is not properly assessed. Inspired by the concept of variable trust, the main contribution of this paper is that we propose a trust assessment method for cloud users based on deep learning. Firstly, we extract users' activities from system logs and employ stacked LSTM (long short-term memory) neural network to model normal activity patterns to build trust profiles for different users. Secondly, the trust profile is capable of predicting future behavioural actions of the specific user, and by calculating the similarity between predicted actions and actual actions the trustworthiness of the user will be assessed with a baseline to detect the trust state of the cloud user dynamically. And in the end, we design and conduct experiments on a public dataset. The results of experiments indicate that when the user is in abnormal state, there are notable differences between predicted actions and user's actual actions, which proves the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposed a robust steganography method for H. 264 without intra-frame distortion drift by using secret sharing. The p embedded secret data was firstly distributed into n sub-secrets with specific polynomial by using (t, n)-threshold multi-secret sharing, then chose the block with prediction mode and chose DCT with paired-coefficients. Then it embeded the embedded data into the paired-coefficients of the 4x4 discrete cosine transform (DCT) block of the selected block. It could restore the hidden data by using the t sub-secrets of the video frames. The experiment results show that the method has the high frame loss and frame error robustness. In addition, the method can avoid intra-frame distortion drift and has better visual concealment. [ABSTRACT FROM AUTHOR]

In the context of rapid urbanization, ecosystem services (ES) losses pose serious threats to sustainability. How to assess ecological risk based on ES value (ESV) has become an urgent problem for sustainable urbanization. However, existing regional ecological risk assessment frameworks ignore important elements, such as the assessment endpoint and uncertainty, weakening their reliability and practicability. In this study, a regional ecological risk assessment framework integrating ESV and uncertainty was proposed by introducing a classical financial indicator, the Sharpe Ratio. We take Hubei Province, Central China as a case and implemented the spatially explicit risk assessment approach based on the methods of the Markov–logistic–CA model, adjusted-based equivalent factor evaluation model, and geographic information system. The results showed that the distribution of expected ecological returns and corresponding uncertainties at county level had a remarkable spatial heterogeneity, and the assessed ecological risk index in Eastern and Western Hubei was higher than that in Central Hubei, indicating that counties in Central Hubei are the priority areas for ecological risk control. Moreover, the expansion of built-up land had the most significant effect on regional ecological risk. This regional ecological risk framework can well integrate the assessment endpoint and dynamic processes of ecological risk. Our assessment framework has potential practical value for ecological risk control and land use planning on ecosystems. Unlabelled Image • A regional ERA framework integrating ESV and uncertainty is proposed. • The proposed framework is used to assess regional ecological risk of Hubei. • Assessed ERI in eastern and western Hubei is higher than that in central Hubei. • Expansion of built-up land has the most effect on regional ecological risk. [ABSTRACT FROM AUTHOR]

This paper proposes a new data hiding method for H.264 without intra-frame distortion drift. The embedded secret data is first distributed into n sub-secrets with matrix equation by using Shamir׳s (t, n)-threshold secret sharing. Then we choose the block with prediction mode and embed the embedded data into discrete cosine transform (DCT) coefficients of the selected block. Finally, we recover the original video as much as possible when the hidden data is extracted out by using the t sub-secrets of the video frames. The experimental results show that this new robust data hiding method not only can get more robustness, effectively avert intra-frame distortion drift and get good visual quality, but also can protect the original video. [ABSTRACT FROM AUTHOR]

This paper proposes a new robust reversible data hiding scheme for H.264. The embedded data is first distributed into n sub-secrets with matrix equation by using Shamir’s (t, n)-threshold secret sharing to improve the robustness of the embedded data. Then we choose the block with prediction mode and embed the sub-secrets into the coefficients of the 4×4 discrete cosine transform (DCT) block of the selected frames which meet our conditions to avert the distortion drift. The experimental results show that this new robust reversible data hiding algorithm can get more robustness, effectively avert intra-frame distortion drift and get good visual quality. [ABSTRACT FROM AUTHOR]