Yifeng Gao

Dr. Yifeng Gao


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 October 2021 in Cryptography
Verified
Journal Article
Open access
PDF file
Hossein SayadiHossein Sayadi
Hossein Sayadi
Yifeng GaoYifeng Gao
Yifeng Gao
HMHosein Mohammadi Makrani
Hosein Mohammadi Makrani
JLJessica Lin
Jessica Lin
PCPaulo Costa
Paulo Costa
HHHouman Homayoun
Houman Homayoun
According to recent security analysis reports, malicious software (a.k.a. malware) is rising at an alarming rate in numbers, complexity, and harmful purposes to compromise the security of modern computer systems. Recently, malware detection based on low-level hardware features (e.g., Hardware Performance Counters (HPCs) information) has emerged as an effective alternative solution to address the complexity and performance overheads of traditional software-based detection methods. Hardware-assisted Malware Detection (HMD) techniques depend on standard Machine Learning (ML) classifiers to detect signatures of malicious applications by monitoring built-in HPC registers during execution at run-time. Prior HMD methods though effective have limited their study on detecting malicious applications that are spawned as a separate thread during application execution, hence detecting stealthy malware patterns at run-time remains a critical challenge. Stealthy malware refers to harmful cyber attacks in which malicious code is hidden within benign applications and remains undetected by traditional malware detection approaches. In this paper, we first present a comprehensive review of recent advances in hardware-assisted malware detection studies that have used standard ML techniques to detect the malware signatures. Next, to address the challenge of stealthy malware detection at the processor’s hardware level, we propose StealthMiner, a novel specialized time series machine learning-based approach to accurately detect stealthy malware trace at run-time using branch instructions, the most prominent HPC feature. StealthMiner is based on a lightweight time series Fully Convolutional Neural Network (FCN) model that automatically identifies potentially contaminated samples in HPC-based time series data and utilizes them to accurately recognize the trace of stealthy malware. Our analysis demonstrates that using state-of-the-art ML-based malware detection methods is not effective in detecting stealthy malware samples since the captured HPC data not only represents malware but also carries benign applications’ microarchitectural data. The experimental results demonstrate that with the aid of our novel intelligent approach, stealthy malware can be detected at run-time with 94% detection performance on average with only one HPC feature, outperforming the detection performance of state-of-the-art HMD and general time series classification methods by up to 42% and 36%, respectively.

4 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
LZLi Zhang
Li Zhang
JDJiahao Ding
Jiahao Ding
Yifeng GaoYifeng Gao
Yifeng Gao
JLJessica Lin
Jessica Lin
Recent rapid development of sensor technology has allowed massive fine-grained time series (TS) data to be collected and set the foundation for the development of data-driven services and applications. During the process, data sharing is often involved to allow the third-party modelers to perform specific time series data mining (TSDM) tasks based on the need of data owner. The high resolution of TS brings new challenges in protecting privacy. While meaningful information in high-resolution TS shifts from concrete point values to local shape-based segments, numerous research have found that long shape-based patterns could contain more sensitive information and may potentially be extracted and misused by a malicious third party. However, the privacy issue for TS patterns is surprisingly seldom explored in privacy-preserving literature. In this work, we consider a new privacy-preserving problem: preventing malicious inference on long shape-based patterns while preserving short segment information for the utility task performance. To mitigate the challenge, we investigate an alternative approach by sharing Matrix Profile (MP), which is a non-linear transformation of original data and a versatile data structure that supports many data mining tasks. We found that while MP can prevent concrete shape leakage, the canonical correlation in MP index can still reveal the location of sensitive long pattern. Based on this observation, we design two attacks named Location Attack and Entropy Attack to extract the pattern location from MP. To further protect MP from these two attacks, we propose a Privacy-Aware Matrix Profile (PMP) via perturbing the local correlation and breaking the canonical correlation in MP index vector. We evaluate our proposed PMP against baseline noise-adding methods through quantitative analysis and real-world case studies to show the effectiveness of the proposed method.

14 February 2025 in arXiv
Verified
Preprint
Open access
PDF file
KGKevin Garcia
Kevin Garcia
JPJuan Manuel Perez
Juan Manuel Perez
Yifeng GaoYifeng Gao
Yifeng Gao
Recently, there has been a significant advancement in designing Self-Supervised Learning (SSL) frameworks for time series data to reduce the dependency on data labels. Among these works, hierarchical contrastive learning-based SSL frameworks, which learn representations by contrasting data embeddings at multiple resolutions, have gained considerable attention. Due to their ability to gather more information, they exhibit better generalization in various downstream tasks. However, when the time series data length is significant long, the computational cost is often significantly higher than that of other SSL frameworks. In this paper, to address this challenge, we propose an efficient way to train hierarchical contrastive learning models. Inspired by the fact that each resolution's data embedding is highly dependent, we introduce importance-aware resolution selection based training framework to reduce the computational cost. In the experiment, we demonstrate that the proposed method significantly improves training time while preserving the original model's integrity in extensive time series classification performance evaluations. Our code could be found here, https://github.com/KEEBVIN/IARS

3 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
LZLi Zhang
Li Zhang
YZYan Zhu
Yan Zhu
Yifeng GaoYifeng Gao
Yifeng Gao
JLJessica Lin
Jessica Lin
Time series motif discovery has been a fundamental task to identify meaningful repeated patterns in time series. Recently, time series chains were introduced as an expansion of time series motifs to identify the continuous evolving patterns in time series data. Informally, a time series chain (TSC) is a temporally ordered set of time series subsequences, in which every subsequence is similar to the one that precedes it, but the last and the first can be arbitrarily dissimilar. TSCs are shown to be able to reveal latent continuous evolving trends in the time series, and identify precursors of unusual events in complex systems. Despite its promising interpretability, unfortunately, we have observed that existing TSC definitions lack the ability to accurately cover the evolving part of a time series: the discovered chains can be easily cut by noise and can include non-evolving patterns, making them impractical in real-world applications. Inspired by a recent work that tracks how the nearest neighbor of a time series subsequence changes over time, we introduce a new TSC definition which is much more robust to noise in the data, in the sense that they can better locate the evolving patterns while excluding the non-evolving ones. We further propose two new quality metrics to rank the discovered chains. With extensive empirical evaluations, we demonstrate that the proposed TSC definition is significantly more robust to noise than the state of the art, and the top ranked chains discovered can reveal meaningful regularities in a variety of real world datasets.

24 September 2025 in arXiv
Verified
Preprint
Open access
PDF file
JPJuan Manuel Perez
Juan Manuel Perez
KGKevin Garcia
Kevin Garcia
BBBrooklyn Berry
Brooklyn Berry
DSDongjin Song
Dongjin Song
Yifeng GaoYifeng Gao
Yifeng Gao
Indexing time series by creating compact binary representations is a fundamental task in time series data mining. Recently, deep learning-based hashing methods have proven effective for indexing time series based on semantic meaning rather than just raw similarity. The purpose of deep hashing is to map samples with the same semantic meaning to identical binary hash codes, enabling more efficient search and retrieval. Unlike other supervised representation learning methods, supervised deep hashing requires a discretization step to convert real-valued representations into binary codes, but this can induce significant information loss. In this paper, we propose a von Mises-Fisher (vMF) hashing loss. The proposed deep hashing model maps data to an M-dimensional hyperspherical space to effectively reduce information loss and models each data class as points following distinct vMF distributions. The designed loss aims to maximize the separation between each modeled vMF distribution to provide a better way to maximize the margin between each semantically different data sample. Experimental results show that our method outperforms existing baselines. The implementation is publicly available at https://github.com/jmpq97/vmf-hashing