Anomaly detection (AD) in time series data is widely applied across various industries for monitoring and security applications, emerging as a key research focus within the field of deep learning. While many methods based on different normality assumptions perform well in specific scenarios, they often neglected the overall normality issue. Some feature extraction methods incorporate pre-training processes but they may not be suitable for time series anomaly detection, leading to decreased performance. Additionally, real-world time series samples are rarely free from noise, making them susceptible to outliers, which further impacts detection accuracy. To address these challenges, we propose a novel anomaly detection method called Robust One-Class Classification Detection (ROC). This approach utilizes an autoencoder (AE) to learn features while constraining the context vectors from the AE within a sufficiently small hypersphere, akin to One-Class Classification (OC) methods. By simultaneously optimizing two hypothetical objective functions, ROC captures various aspects of normality. We categorize the input raw time series into clean and outlier sequences, reducing the impact of outliers on compressed feature representation. Experimental results on public datasets indicate that our approach outperforms existing baseline methods and substantially improves model robustness.

Deep neural networks remain susceptible to adversarial examples, where the goal of an adversarial attack is to introduce small perturbations to the original examples in order to confuse the model without being easily detected. Although many adversarial attack methods produce adversarial examples that have achieved great results in the white-box setting, they exhibit low transferability in the black-box setting. In order to improve the transferability along the baseline of the gradient-based attack technique, we present a novel Stochastic Gradient Accumulation Momentum Iterative Attack (SAMI-FGSM) in this study. In particular, during each iteration, the gradient information is calculated using a normal sampling approach that randomly samples around the sample points, with the highest probability of capturing adversarial features. Meanwhile, the accumulated information of the sampled gradient from the previous iteration is further considered to modify the current updated gradient, and the original gradient attack direction is changed to ensure that the updated gradient direction is more stable. Comprehensive experiments conducted on the ImageNet dataset show that our method outperforms existing state-of-the-art gradient-based attack techniques, achieving an average improvement of 10.2% in transferability.

A Location-Based Service (LBS) refers to geolocation-based services that bring both convenience and vulnerability. With an increase in the scale and value of data, most existing location privacy protection protocols cannot balance privacy and utility. To solve the revealing problems in LBS, we propose a differential privacy protection protocol based on location entropy. First, we design an algorithm of the best-assisted user selection for constructing anonymity sets. Second, we employ smart contracts to evaluate the credibility of participants, which ensures the honesty of participants. Moreover, we provide a comprehensive experiment; the theoretical analysis and experiments show that the proposed protocol effectively resists background knowledge attacks. Generally, our protocol improves data availability. Particularly, it realizes user-controllable privacy protection, which improves privacy protection and strengthens security.