Over the last years, sensor-based continuous authentication on mobile devices has achieved great success on personal information protection. These proposed mechanisms, however, require both legal and illegal users'...
详细信息
Over the last years, sensor-based continuous authentication on mobile devices has achieved great success on personal information protection. These proposed mechanisms, however, require both legal and illegal users' data for authentication model training, which takes time and is impractical. In this paper, we present MAuGANs, a lightweight and practical memory-augmented autoencoder-based continuous Authentication system on smartphones with conditional transformer Generative Adversarial Networks (GANs), where the conditional transformer GANs (CTGANs) are used for data augmentation and the memory-augmented autoencoder (MAu) is utilized to identify users. Specifically, MAuGANs exploits the smartphone built-in accelerometer and gyroscope sensors to implicitly collect users' behavioral patterns. With the normalized legitimate user's sensor data, MAuGANs uses a CTGAN composed of a conditional transformer-based generator and a conditional transformer-based discriminator to create additional training data for the MAu. Then, the MAu is trained on the augmented legitimate user's data. The trained MAu reconstructs the current user data and then calculates the reconstruction error between the reconstructed data and current user data. To carry out user authentication, MAuGANs compares the reconstruction error with a predefined authentication threshold. We evaluate the performance of MAuGANs on our dataset, where our extensive experiments demonstrate that MAuGANs reaches the best authentication performance, when comparing with the representative state-of-the-art methods, by 0.33% EER and 99.65% accuracy on 10 unseen users.
In recent years, attacks on network environments continue to rapidly advance and are increasingly intelligent. Accordingly, it is evident that there are limitations in existing signature-based intrusion detection syst...
详细信息
In recent years, attacks on network environments continue to rapidly advance and are increasingly intelligent. Accordingly, it is evident that there are limitations in existing signature-based intrusion detection systems. In particular, for novel attacks such as Advanced Persistent Threat (APT), signature patterns have problems with poor generalization performance. Furthermore, in a network environment, attack samples are rarely collected compared to normal samples, creating the problem of imbalanced data. Anomaly detection using an autoencoder has been widely studied in this environment, and learning is through semi-supervised learning methods to overcome these problems. This approach is based on the assumption that reconstruction errors for samples that are not used for training will be large, but an autoencoder is often over-generalized and this assumption is often broken. In this paper, we propose a network intrusion detection method using a memory-augmented deep auto-encoder (MemAE) that can solve the over-generalization problem of autoencoders. The MemAE model is trained to reconstruct the input of an abnormal sample that is close to a normal sample, which solves the generalization problem for such abnormal samples. Experiments were conducted on the NSL-KDD, UNSW-NB15, and CICIDS 2017 datasets, and it was confirmed that the proposed method is better than other one-class models.
Indoor air quality (IAQ) monitoring in subway stations depends on sensors prone to failures due to confined spaces, cyberattacks, and prolonged use. Soft sensor validation frameworks using statistical or machine learn...
详细信息
Indoor air quality (IAQ) monitoring in subway stations depends on sensors prone to failures due to confined spaces, cyberattacks, and prolonged use. Soft sensor validation frameworks using statistical or machine learning models can detect, diagnose, and reconstruct faulty data but struggle with complex fault patterns. This study introduces a memory-augmented autoencoder-based framework for reliable IAQ sensor validation, leveraging memorized normal prototypes. To the best of our knowledge, this is the first validation method that utilizes normal prototypes for reconciling corrupted measurements. Tested on real IAQ data from Seoul Metro's C-station, the method achieved a 97.03% detection rate, a 4.33% false alarm rate, and demonstrated potential for 10.25% energy savings while maintaining healthy IAQ.
With the advancement of network communication technology,network traffic shows explosive ***,network attacks occur *** intrusion detection systems are still the primary means of detecting ***,two challenges continue t...
详细信息
With the advancement of network communication technology,network traffic shows explosive ***,network attacks occur *** intrusion detection systems are still the primary means of detecting ***,two challenges continue to stymie the development of a viable network intrusion detection system:imbalanced training data and new undiscovered ***,this study proposes a unique deep learning-based intrusion detection *** use two independent in-memoryautoencoders trained on regular network traffic and attacks to capture the dynamic relationship between traffic features in the presence of unbalanced training *** the original data is fed into the triplet network by forming a triplet with the data reconstructed from the two encoders to ***,the distance relationship between the triples determines whether the traffic is an *** addition,to improve the accuracy of detecting unknown attacks,this research proposes an improved triplet loss function that is used to pull the distances of the same class closer while pushing the distances belonging to different classes farther in the learned feature *** proposed approach’s effectiveness,stability,and significance are evaluated against advanced models on the Android Adware and General Malware Dataset(AAGM17),Knowledge Discovery and Data Mining Cup 1999(KDDCUP99),Canadian Institute for Cybersecurity Group’s Intrusion Detection Evaluation Dataset(CICIDS2017),UNSW-NB15,Network Security Lab-Knowledge Discovery and Data Mining(NSL-KDD)*** achieved results confirmed the superiority of the proposed method for the task of network intrusion detection.
With the advent of the industrial information age, the scale and complexity of cyber-physical systems (CPS) are increasing. In this environment, cyber attacks against CPS are on the rise. To ensure the proper operatio...
详细信息
ISBN:
(数字)9781665471800
ISBN:
(纸本)9781665471800
With the advent of the industrial information age, the scale and complexity of cyber-physical systems (CPS) are increasing. In this environment, cyber attacks against CPS are on the rise. To ensure the proper operation of CPS, unsupervised anomaly detection methods for CPS become very important. Current unsupervised anomaly detection work usually uses autoencoder model. However, autoencoder may suffer from over-generalization problems resulting in abnormal missed detection. Also, some works do not consideration of the temporal information about the data and will ignore contextual anomalies. In this paper, we propose a memory-augmented deep autoencoder with predictive analytics (MemAE-P) for CPS unsupervised anomaly detection method, which simultaneously predicts and reconstructs the input data, overcoming the drawback of using each one alone. Specifically, we use a memory module to help the autoencoder reconstruction converge to normal samples to enhance the anomalous reconstruction error and avoid the generalization problem of anomalous samples. The attention-based Bi-LSTM is explored, which captures temporal dependence of CPS multi-sensor data, to predict the next moment sample given multiple previous moment samples. We consider reconstruction error and prediction error of input data to distinguish abnormal data from normal data. In addition, we use the error obtained from the model to infer which devices in the anomaly sample are most likely to be attacked. We demonstrated the effectiveness of MemAE-P through various experiments on three real CPS datasets.
暂无评论