10 February 2023 in IEEE Transactions on Computational Social Systems
Nowadays, the emergence of online trading greatly facilitates people’s life. Meanwhile, online trading also brings hidden dangers, such as online fraudulent trading. To solve the issue, researchers have proposed many different detection models. However, in actual business scenarios, fraudulent transactions usually only account for a small portion of normal transactions, resulting in extremely imbalanced data. Besides, the concealment of fraud is reflected in that the fraudsters are imitating the normal transactions of users, posing a huge challenge for fraudulent transaction detection modeling. Inspired by generative adversarial networks (GANs), we propose a GAN-based framework to detect online banking fraud on extremely imbalanced data, called BalanceGAN. A fraud detection model is first pretrained using the data generated by the generator and then the model is fine-tuned using transfer learning on real-world datasets, by using this approach to address data imbalances. Compared with the conventional methods for solving imbalanced data, our BalanceGAN can avoid over-fitting of the model relatively, experiments on two real datasets show that our BalanceGAN has more than 10% performance improvement in Precision and Recall.
12 July 2022 in IEEE Transactions on Big Data
Local differential privacy (LDP) is a prevalent measure of privacy protection as it provides rigorous privacy guarantees and has been widely studied for statistical analysis, especially in frequency estimation. As a representative LDP-enabled frequency estimation algorithm, Google’s Randomized Aggregation Privacy-Preserving Ordinal Response (RAPPOR) has been put into practice. However, it achieves sub-optimal utility due to the following limitations. Firstly, the adoption of the MD5 hash function inevitably results in the hash collision. Secondly, the application of the randomized response technique leads to randomness. To improve the practical effectiveness of RAPPOR and the utility of frequency-based services, we propose an LDP-enabled frequency estimation method called PK-RAPPOR, in which we devise an effective re-encoding hash function (RE-HF) incorporating prior knowledge (PK) about the rough frequency ranking of items. RE-HF divides items into several cohorts based on the PK and generates a unique hash value set for each item. Compared with the original RAPPOR, the hash collision can be eliminated for items from different cohorts, and the effect of randomness can be decreased by the overlapping of items from the same cohorts. We validate our proposed method with theoretical analysis and demonstrate its effectiveness with experiments on both synthetic and real-world datasets.
16 January 2023 in ACM Transactions on Management Information Systems
Data collection underlocal differential privacy (LDP)has been gradually on the stage. Compared with the implementation of LDP on the single attribute data collection, that on multi-dimensional data faces great challenges as follows: (1)Communication cost. Multivariate data collection needs to retain the correlations between attributes, which means that more complex privatization mechanisms will result in more communication costs. (2)Noise scale. More attributes have to share the privacy budget limited by data utility and privacy-preserving level, which means that less privacy budget can be allocated to each of them, resulting in more noise added to the data. In this work, we innovatively reverse the complex multi-dimensional attributes, i.e., the majornegativefactor that leads to the above difficulties, to act as abeneficialfactor to improve the efficiency of privacy budget allocation, so as to realize a multi-dimensional data collection under LDP with high comprehensive performance. Specifically, we first present aMultivariatek-ary Randomized Response (kRR)mechanism, calledMulti-kRR. It applies the RR directly to each attribute to reduce the communication cost. To deal with the impact of a large amount of noise, we propose a Markov-based dynamic privacy budget allocation mechanism Markov-kRR, which determines the present privacy budget (flipping probability) of an attribute related to the state of the previous attributes. Then, we fix the threshold of flipping times in Markov-kRR and propose an improved mechanism called MarkFixed-kRR, which can obtain more optimized utility by choosing the suitable threshold. Finally, extensive experiments demonstrate the efficiency and effectiveness of our proposed methods.
11 December 2024 in IEEE Transactions on Information Forensics and Security
Data sharing facilitates the integration and in-depth exploration of cross-domain data, thereby fostering innovative research and model development. However, privacy leakage emerges as a critical barrier to the sharing and circulating of such data. Existing privacy-preserving technologies face challenges in handling complex scenarios involving multiple participants due to the following reasons: 1) Divergent privacy permission. Data sharing is constrained by various privacy limitations, necessitating the consideration of privacy permissions across different domains, akin to a cross-border process. 2) High collaboration cost. Collaboration among multiple domains to determine the privacy constraint and sharing ways incur additional costs. 3) Large noise magnitude. Traditional privacy techniques to protect the privacy of a single domain using local differential privacy (LDP) may introduce excessive noise, thereby reducing data utility. Drawing inspiration from the cross-border visa issuance process, we present an innovative framework called PriVisa for enabling privacy-preserving data sharing across different domains. It consists of four key modules to overcome the mentioned challenges: the hybrid pattern, optimized sharing path construction, personalized grouping, and LDP-based perturbation. 1) The hybrid pattern for coordination among organizations, considering authentication, privacy constraints, and sharing methods. 2) The optimized sharing path construction using a privacy constraint hierarchy tree to maximize data utility while adhering to privacy requirements. 3) The feature similarity grouping and perturbing mechanism satisfying LDP to protect privacy and optimize data utility. The theoretical and experimental validation confirms PriVisa’s effectiveness in addressing divergent privacy constraints and promoting data utility in cross-domain data sharing.
25 July 2022 in Security and Safety
This paper addresses a special and imperceptible class of privacy, called implicit privacy. In contrast to traditional (explicit) privacy, implicit privacy has two essential properties: (1) It is not initially defined as a privacy attribute; (2) it is strongly associated with privacy attributes. In other words, attackers could utilize it to infer privacy attributes with a certain probability, indirectly resulting in the disclosure of private information. To deal with the implicit privacy disclosure problem, we give a measurable definition of implicit privacy, and propose an ex-ante implicit privacy-preserving framework based on data generation, called IMPOSTER. The framework consists of an implicit privacy detection module and an implicit privacy protection module. The former uses normalized mutual information to detect implicit privacy attributes that are strongly related to traditional privacy attributes. Based on the idea of data generation, the latter equips the Generative Adversarial Network (GAN) framework with an additional discriminator, which is used to eliminate the association between traditional privacy attributes and implicit ones. We elaborate a theoretical analysis for the convergence of the framework. Experiments demonstrate that with the learned generator, IMPOSTER can alleviate the disclosure of implicit privacy while maintaining good data utility.