arXiv subjects

Cheng Hong

Publications and source records attributed to Cheng Hong.

25 records · Page 2Linked to original sources

arXiv2021

Revisiting $k$-Nearest Neighbor Graph Construction on High-Dimensional Data : Experiments and Analyses

The $k$-nearest neighbor graph (KNNG) on high-dimensional data is a data structure widely used in many applications such as similarity search, dimension reduction and clustering. Due to its increasing popularity, several methods under the same framework have been proposed in the past decade. This framework contains two steps, i.e. building an initial KNNG (denoted as \texttt{INIT}) and then refining it by neighborhood propagation (denoted as \texttt{NBPG}). However, there remain several questions to be answered. First, it lacks a comprehensive experimental comparison among representative solutions in the literature. Second, some recently proposed indexing structures, e.g., SW and HNSW, have not been used or tested for building an initial KNNG. Third, the relationship between the data property and the effectiveness of \texttt{NBPG} is still not clear. To address these issues, we comprehensively compare the representative approaches on real-world high-dimensional data sets to provide practical and insightful suggestions for users. As the first attempt, we take SW and HNSW as the alternatives of \texttt{INIT} in our experiments. Moreover, we investigate the effectiveness of \texttt{NBPG} and find the strong correlation between the huness phenomenon and the performance of \texttt{NBPG}.

cs.DS↗

arXiv2021

When Homomorphic Encryption Marries Secret Sharing: Secure Large-Scale Sparse Logistic Regression and Applications in Risk Control

Logistic Regression (LR) is the most widely used machine learning model in industry for its efficiency, robustness, and interpretability. Due to the problem of data isolation and the requirement of high model performance, many applications in industry call for building a secure and efficient LR model for multiple parties. Most existing work uses either Homomorphic Encryption (HE) or Secret Sharing (SS) to build secure LR. HE based methods can deal with high-dimensional sparse features, but they incur potential security risks. SS based methods have provable security, but they have efficiency issue under high-dimensional sparse features. In this paper, we first present CAESAR, which combines HE and SS to build secure large-scale sparse logistic regression model and achieves both efficiency and security. We then present the distributed implementation of CAESAR for scalability requirement. We have deployed CAESAR in a risk control task and conducted comprehensive experiments. Our experimental results show that CAESAR improves the state-of-the-art model by around 130 times.

cs.CR↗

arXiv2020

Improving Utility and Security of the Shuffler-based Differential Privacy

When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator. LDP imposes large amount of noise as each user executes the randomization independently. To address this issue, recent work introduced an intermediate server with the assumption that this intermediate server does not collude with the aggregator. Under this assumption, less noise can be added to achieve the same privacy guarantee as LDP, thus improving utility for the data collection task. This paper investigates this multiple-party setting of LDP. We analyze the system model and identify potential adversaries. We then make two improvements: a new algorithm that achieves a better privacy-utility tradeoff; and a novel protocol that provides better protection against various attacks. Finally, we perform experiments to compare different methods and demonstrate the benefits of using our proposed method.

cs.CR↗

arXiv2020

Quantification of the Leakage in Federated Learning

With the growing emphasis on users' privacy, federated learning has become more and more popular. Many architectures have been raised for a better security. Most architecture work on the assumption that data's gradient could not leak information. However, some work, recently, has shown such gradients may lead to leakage of the training data. In this paper, we discuss the leakage based on a federated approximated logistic regression model and show that such gradient's leakage could leak the complete training data if all elements of the inputs are either 0 or 1.

cs.CR↗

arXiv2020

Secure Social Recommendation based on Secret Sharing

Nowadays, privacy preserving machine learning has been drawing much attention in both industry and academy. Meanwhile, recommender systems have been extensively adopted by many commercial platforms (e.g. Amazon) and they are mainly built based on user-item interactions. Besides, social platforms (e.g. Facebook) have rich resources of user social information. It is well known that social information, which is rich on social platforms such as Facebook, are useful to recommender systems. It is anticipated to combine the social information with the user-item ratings to improve the overall recommendation performance. Most existing recommendation models are built based on the assumptions that the social information are available. However, different platforms are usually reluctant to (or cannot) share their data due to certain concerns. In this paper, we first propose a SEcure SOcial RECommendation (SeSoRec) framework which can (1) collaboratively mine knowledge from social platform to improve the recommendation performance of the rating platform, and (2) securely keep the raw data of both platforms. We then propose a Secret Sharing based Matrix Multiplication (SSMM) protocol to optimize SeSoRec and prove its correctness and security theoretically. By applying minibatch gradient descent, SeSoRec has linear time complexities in terms of both computation and communication. The comprehensive experimental results on three real-world datasets demonstrate the effectiveness of our proposed SeSoRec and SSMM.

cs.LG↗

arXiv2020

Privacy-preserving collaborative machine learning on genomic data using TensorFlow

Machine learning (ML) methods have been widely used in genomic studies. However, genomic data are often held by different stakeholders (e.g. hospitals, universities, and healthcare companies) who consider the data as sensitive information, even though they desire to collaborate. To address this issue, recent works have proposed solutions using Secure Multi-party Computation (MPC), which train on the decentralized data in a way that the participants could learn nothing from each other beyond the final trained model. We design and implement several MPC-friendly ML primitives, including class weight adjustment and parallelizable approximation of activation function. In addition, we develop the solution as an extension to TF Encrypted~\citep{dahl2018private}, enabling us to quickly experiment with enhancements of both machine learning techniques and cryptographic protocols while leveraging the advantages of TensorFlow's optimizations. Our implementation compares favorably with state-of-the-art methods, winning first place in Track IV of the iDASH2019 secure genome analysis competition.

cs.CR↗

arXiv2017

High Quality of Electromagnetically Induced Transparency Spectroscopy of 87Rb in a Buffer Gas Cell with Magnetic Field

We have studied the phenomenon of electromagnetically induced transparency (EIT) of 87Rb vapor with a buffer gas in a magnetic field at room temperature. It is found that the spectral lines caused by the velocity selective optical pump effects get much weaker and wider when the sample cell mixed with a 5-Torr N2 gas while the EIT signal kept almost unchanged. A weighted least-square fit is also developed to remove the Doppler broadening completely. This spectral method provides a way to measure the Zeeman splitting with high resolution, for example, the Λ-type EIT resonance splits into four peaks on the D2 line of 87Rb in the thermal 2-cm vapor cell with a magnetic field along the electric field of the linearly polarized coupling laser. The high resolution spectrum can be used to lock the laser to a given frequency by tuning the magnetic field.

physics.atom-ph↗