Agent-based simulations have been used in modeling transportation systems for traffic management and passenger flows. In this work, we hope to shed light on the complex factors that influence transportation mode decis...
The increasing demand for IoT devices in industries has generated a high level of cybersecurity threats, with botnets including Mozi exploiting poor passwords and unpatched vulnerabilities to target networked infrastr...
详细信息
ISBN:
(数字)9798331515478
ISBN:
(纸本)9798331515485
The increasing demand for IoT devices in industries has generated a high level of cybersecurity threats, with botnets including Mozi exploiting poor passwords and unpatched vulnerabilities to target networked infrastructure. Peer-to-peer (P2P) topology of Mozi, employing Distributed Hash Tables (DHTs) for Command-and-Control (C2) communications, makes it resistant to takedown operations and capable of high-scale Distributed Denial-of-Service (DDoS) attack, data exfiltration, and remote command execution. Traditional one-class, machine learning techniques such as OneClass Support Vector Machine (OCSVM) and Local Outlier Factor (LOF) have been widely used for discovering malwarerelated anomalies. However, such techniques require high labelled training datasets, whose availability in dynamically changing environments of malwares proves challenging. In this work, an AutoRegressive Integrated Moving Average (ARIMA)-based mechanism for discovering time-series anomalies in IoT-infected devices with Mozi infection is proposed. In an experimental setup using a Raspberry Pi running Pi-hole, baseline profiles of CPU consumption, RAM usage, and network activity are first established under normal conditions. Next, a system is subjected to a simulation of infection with Mozi malware and monitored for deviation with ARIMA forecasting and Local Outlier Factor (LOF) for discovering anomalies. By comparing predicted values with actual values, effective intrusion detection for malware-related anomalies is attained, providing a real-time, adaptive mechanism for early intrusion detection. In conclusion, with its effectiveness in discovering stealthy behaviour of malwares, employing ARIMA for discovering time-series anomalies in IoTinfected devices proves effective, and its employment in IoT cybersecurity aids in providing real-time mechanism for discovering threats for system admins and security professionals. As future work, a combination of ARIMA with deep neural networks such as Long
Machine learning typically relies on the assumption that training and testing distributions are identical and that data is centrally stored for training and testing. However, in real-world scenarios, distributions may...
详细信息
Remote driving serves as a viable solution in situations where fully autonomous vehicles encounter critical events, such as sensor failures. However, implementing remote driving poses certain technical challenges, inc...
Remote driving serves as a viable solution in situations where fully autonomous vehicles encounter critical events, such as sensor failures. However, implementing remote driving poses certain technical challenges, including the need to ensure high-quality video transmission to the remote driver. Additionally, in scenarios involving poor road conditions, multiple autonomous vehicles may simultaneously require remote driving assistance at specific locations, straining the communication infrastructure. To address these challenges, we propose a novel approach that involves compression of the driving video using a driving safety model. This model intelligently prioritizes key objects within the frame, resulting in improved compression quality. An initial experiment demonstrated that 60% of the required bitrate can be reduced while retaining 90% of the perceived quality.
In recent years, support vector machine has become one of the most important classification techniques in pattern recognition, machine learning, and data mining due to its superior classification effect and solid theo...
详细信息
In this paper, we propose a method for defending against audio adversarial examples that operates by applying audio style transfer learning. The proposed method has the effect of maintaining the classification result ...
详细信息
In this paper, we propose a method for defending against audio adversarial examples that operates by applying audio style transfer learning. The proposed method has the effect of maintaining the classification result produced by the target model and removing the adversarial noise by changing only the style while maintaining the content of the input audio sample. In an experimental evaluation using the Mozilla Common Voice dataset as the test data source and TensorFlow as the machine learning library, the proposed method improved the target model’s accuracy on the adversarial examples from 2.1% to 79.2% while maintaining its accuracy on the original samples at 81.4%. Author
Neural architecture search (NAS) automates the design of neural networks, but faces high computational costs for evaluating the performance candidate architectures. Surrogate-assisted NAS methods use approximate compu...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
Neural architecture search (NAS) automates the design of neural networks, but faces high computational costs for evaluating the performance candidate architectures. Surrogate-assisted NAS methods use approximate computational models to get predictive estimation instead of real complete training, but also face the challenge of maintaining the balance between training cost and predictive effectiveness. In this paper, we propose a progressive neural predictor that uses score-based sampling (PNSS) to improve the performance of the surrogate model with limited training data. Different from existing algorithms that rely on initial sample selection, PNSS uses an online method to progressively select new samples of the surrogate model based on potential information from the previous search process. During the iterative process, the sampled scores are dynamically adjusted based on the prediction rankings in each round to keep track of good architectures, which gradually optimises the surrogate model. In this way, the processes of training the predictor and searching for architectures are jointly combined to improve the efficiency of sample utilization. In addition, the surrogate model with different degrees of training is assigned prediction confidence equal to the accuracy of the current stage. Experiments are conducted on NAS-Bench-101 and NAS-Bench-201 benchmarks. The experimental results show that the proposed PNSS algorithm outperforms the existing methods with limited training samples. In addition, visualisation of the search process and ablation study also shows the effectiveness of the progressive search.
Networks are essential models in many applications such as information technology, chemistry, power systems, transportation, neuroscience, and social sciences. In light of such broad applicability, a general theory of...
详细信息
Hyperledger Fabric stands as a leading framework for permissioned block-chain systems, ensuring data security and audit-ability for enterprise applications. As applications on this platform grow, understanding its com...
详细信息
ISBN:
(数字)9798350327939
ISBN:
(纸本)9798350327946
Hyperledger Fabric stands as a leading framework for permissioned block-chain systems, ensuring data security and audit-ability for enterprise applications. As applications on this platform grow, understanding its complex configuration concerning various block-chain parameters becomes vital. These configurations significantly affect the system’s performance and cost. In this research, we introduce a Stochastic Petri Net (SPN) model to analyze Hyper-ledger Fabric’s performance, considering variations in block-chain parameters, computational resources, and transaction rates. We provide case studies to validate the utility of our model, aiding block-chain administrators in determining optimal configurations for their applications. A key observation from our model highlights the block size’s role in system response time. We noted an increased mean response time, between 1 to 25 seconds, due to variations in transaction arrival rates.
暂无评论