Author name cluster

Xiaofeng Liao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

JMLR Journal 2023 Journal Article

Accelerated Primal-Dual Mirror Dynamics for Centralized and Distributed Constrained Convex Optimization Problems

You Zhao
Xiaofeng Liao
Xing He
Mingliang Zhou
Chaojie Li

This paper investigates two accelerated primal-dual mirror dynamical approaches for smooth and nonsmooth convex optimization problems with affine and closed, convex set constraints. In the smooth case, an accelerated primal-dual mirror dynamical approach (APDMD) based on accelerated mirror descent and primal-dual framework is proposed and accelerated convergence properties of primal-dual gap, feasibility measure and the objective function value along with trajectories of APDMD are derived by the Lyapunov analysis method. Then, we extend APDMD into two distributed dynamical approaches to deal with two types of distributed smooth optimization problems, i.e., distributed constrained consensus problem (DCCP) and distributed extended monotropic optimization (DEMO) with accelerated convergence guarantees. Moreover, in the nonsmooth case, we propose a smoothing accelerated primal-dual mirror dynamical approach (SAPDMD) with the help of smoothing approximation technique and the above APDMD. We further also prove that primal-dual gap, objective function value and feasibility measure along with trajectories of SAPDMD have the same accelerated convergence properties as APDMD by choosing the appropriate smooth approximation parameters. Later, we propose two smoothing accelerated distributed dynamical approaches to deal with nonsmooth DEMO and DCCP to obtain accelerated and efficient solutions. Finally, numerical and comparative experiments are given to demonstrate the effectiveness and superiority of the proposed accelerated mirror dynamical approaches. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

TIST Journal 2023 Journal Article

Towards Query-Efficient Black-Box Attacks: A Universal Dual Transferability-Based Framework

Tao Xiang
Hangcheng Liu
Shangwei Guo
Yan Gan
Wenjian He
Xiaofeng Liao

Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations. However, all pixels are not equally crucial to the target model; thus, indiscriminately treating all pixels will increase query overhead inevitably. In addition, existing black-box attacks take clean samples as start points, which also limits query efficiency. In this article, we propose a novel black-box attack framework, constructed on a strategy of dual transferability (DT), to perturb the discriminative areas of clean examples within limited queries. The first kind of transferability is the transferability of model interpretations. Based on this property, we identify the discriminative areas of clean samples for generating local perturbations. The second is the transferability of adversarial examples, which helps us to produce local pre-perturbations for further improving query efficiency. We achieve the two kinds of transferability through an independent auxiliary model and do not incur extra query overhead. After identifying discriminative areas and generating pre-perturbations, we use the pre-perturbed samples as better start points and further perturb them locally in a black-box manner to search the corresponding adversarial examples. The DT strategy is general; thus, the proposed framework can be applied to different types of black-box attacks. We conduct extensive experiments to show that, under various system settings, our framework can significantly improve the query efficiency of existing black-box attacks and attack success rates.

Details DOI

EAAI Journal 2019 Journal Article

A novel algorithm for privacy preserving utility mining based on integer linear programming

Shaoxin Li
Nankun Mu
Junqing Le
Xiaofeng Liao

As an important research topic, high-utility itemset mining (HUIM) has, of late years, attracted increasing attention, where both the significance and quantity factors of items are taken into account to mine high-utility itemsets (HUIs). Privacy breaches have always been a major issue existing in the field of data mining, which usually inevitably arise, especially when private data collections are publicly published or shared by organizations. To tackle this problem, plentiful methodologies regarding privacy-preserving data mining (PPDM) have been proposed. Due to the high practicality of HUIM, in recent years, privacy-preserving utility mining (PPUM) has become a popular research orientation in PPDM. The main goal of PPUM is to hide sensitive HUIs (SHUIs) so as to leave no confidential information uncovered in the resulting sanitized database. However, all the previously proposed approaches have suffered from the defect of introducing numerous side effects by performing database perturbation. To alleviate this issue, in this paper, a novel algorithm based on integer linear programming (ILP) is proposed to obtain a lower ratio of side effects produced in the hiding process while does not reveal any sensitive information in the sanitized database. We formulate the hiding process as a constraint satisfaction problem (CSP), which pursuing the protection of SHUIs as well as the minimization of side effects. A solution to the hiding problem is expected to be obtained by exploiting ILP technique to solve the mapped problem, which properly indicates the processing manner of perturbation operation. In addition, a relaxation procedure is also adopted in the designed algorithm to provide an approximate solution of the CSP when the optimal one does not exist. Extensive experimental evaluations between our proposed method and other state-of-the-art algorithms are conducted on several real-world datasets. The comparative results demonstrate the superiorities of the proposed algorithm with respect to running time and the ability to minimize side effects.

Details DOI

TCS Journal 2014 Journal Article

Period distribution of generalized discrete Arnold cat map

Fei Chen
Kwok-wo Wong
Xiaofeng Liao
Tao Xiang

The generalized discrete Arnold cat map is adopted in various cryptographic and steganographic applications where chaos is employed. In this paper, we analyze the period distribution of this map. A systematic approach for addressing the general period distribution problem for any integer value of the modulus N is outlined, followed by a complete analysis for the case of prime N. The analysis is based on similar techniques studying linear feedback shift register (LFSR) sequences. Together with our previous results when N is a power of a prime [1, 2], the period distribution of the cat map is characterized nearly completely for any integer N. Our results are also useful for evaluating the security of the cryptographic and steganographic algorithms based on the cat map as well as computing all unstable periodic orbits of the chaotic Arnold cat map.

Details DOI

TCS Journal 2012 Journal Article

Verifiable multi-secret sharing based on LFSR sequences

Chunqiang Hu
Xiaofeng Liao
Xiuzhen Cheng

In verifiable multi-secret sharing schemes (VMSSs), many secrets can be shared but only one share is kept by each user and this share is verifiable by others. In this paper, we propose two secure, efficient, and verifiable ( t, n ) multi-secret sharing schemes, namely Scheme-I and Scheme-II. Scheme-I is based on the Lagrange interpolating polynomial and the LFSR-based public key cryptosystem. The Lagrange interpolating polynomial is used to split and reconstruct the secrets and the LFSR-based public key cryptosystem is employed to verify the validity of the data. Scheme-II is designed according to the LFSR sequence and the LFSR-based public key cryptosystem. We compare our schemes with the state-of-the-art in terms of attack resistance, computation complexity, and so on, and conclude that our schemes have better performance and incur less computation overhead. Our schemes can effectively detect a variety of forgery or cheating actions to ensure that the recovery of the secrets is secure and creditable, and the length of the private key is only one third of that of others for the same security level.

Details DOI