Guangke Chen
Guangke Chen (陈光科)

Ph.D Student at ShanghaiTech University

GoogleScholar
researchgate
github
github
github
Zhihu
Twitter
linkedin

About Me

[CV-en] [简历-中文]

I am currently a final-year Ph.D student in ShanghaiTech University (2019.09-today), majoring in Computer Science. I am a member of System and Software Security Lab (S3L) and advised by Prof. Fu Song, the PI of S3L.

I received my Bachelor's degree (2015.09-2019.06, major: Information Engineering) in South China University of Technology, Guangzhou. 💫

Research Interests

[Research Summary]

  • Security and privacy of machine learning (e.g., voiceprint recognition and speech recognition)
  • Security and privacy of multimedia (e.g., speech)

I am expected to graduate in June 2024 and I'm on the job market (acadamia/industry). Consider dropping me an email if you have any suitable opportunities.

News

  • [2023.11] Awarded with Merit Student in ShanghaiTech.
  • [2023.10] Awarded with National Scholarship for Ph.D student (top 2%)
  • [2023.9] 'SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems' accepted by NDSS 2024
  • [2023.5] 'QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems' accepted by USENIX Security 2023
  • [2023.2] Invited as reviewer of ISCA INTERSPEECH 2023.
  • [2022.12] Awarded with Merit Student in ShanghaiTech.
  • More

Publications

  • SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems

    NDSS 2024, CCF-A

    Guangke Chen, Yedi Zhang, and Fu Song

    [paper] [code]

  • QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems

    USENIX Security 2023, CCF-A

    Guangke Chen, Yedi Zhang, Zhe Zhao, and Fu Song

    [paper] [website] [slide] [talk] [press]

    💥 🔥 highly effective against commercial APIs and voice assistants

    🌟 vulnerability disclosure received bounty award from vendor

  • Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition

    IEEE Transactions on Dependable and Secure Computing (TDSC), CCF-A, IF=7.3

    Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan, Feng Wang, and Jiashui Wang

    [paper] [code] [website] [slide]

  • Precise Quantitative Analysis of Binarized Neural Networks: A BDD-based Approach

    ACM Transactions on Software Engineering and Methodology (TOSEM, CCF-A)

    Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, and Taolue Chen

  • QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks

    ASE 2022, CCF-A

    Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Min Zhang, Taulue Chen, and Jun Sun

    [paper] [code]

  • CLEVEREST: Accelerating CEGAR-based Neural Network Verification via Adversarial Attacks

    SAS 2022, CCF-B

    Zhe Zhao, Yedi Zhang, Guangke Chen, Fu Song, Taolue Chen and Jiaxiang Liu

    [paper]

  • AS2T: Arbitrary source-to-target adversarial attack on speaker recognition systems

    IEEE Transactions on Dependable and Secure Computing (TDSC), CCF-A, IF=7.3

    Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan, and Yang Liu

    [paper] [blog]

  • Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples

    ACM Transactions on Software Engineering and Methodology (TOSEM, CCF-A)

    Zhe Zhao, Guangke Chen, Tong Liu, Taishan Li, Fu Song, Jingyi Wang, and Jun Sun

  • SEC4SR: A Security Analysis Platform for Speaker Recognition

    Preprint

    Guangke Chen, Zhe Zhao, Fu Song, Sen Chen, Lingling Fan, and Yang Liu

    [paper] [code] [website]

  • Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems

    Oakland 2021, CCF-A, AR:115/952=12%

    Guangke Chen, Sen Chen, Lingling Fan, Xiaoning Du, Zhe Zhao, Fu Song, and Yang Liu

    [paper] [website] [code] [slide] [talk] [blog] [press-1] [press-2] [press-3]

    💥 🔥 🌟 citations > 170

  • Attack as Defense: Characterizing Adversarial Examples using Robustness

    ISSTA 2021, CCF-A, AR=51/219=23%

    Zhe Zhao, Guangke Chen, Jingyi Wang, Yiwei Yang, Fu Song, and Jun Sun

    [paper] [code]

  • BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks

    CAV 2021, CCF-A, AR=79/290=27%

    Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, and Taolue Chen

    [paper]

  • Detail and More

Patent

Granted

  • A deep learning-based approach for distinguishing abnormal speech | Xiaohui Feng, Guangke Chen, Qianhua He, Xiaolan Wu, Yanxiong Li | CN108766419B | 2020.10.27
  • Method and apparatus for monitoring psychological stress with integration of pulse rate variability and sleep quality | Xiaofen Xing, Guangke Chen, Shiyao Jiang, Litao Lin, Donghua Chen | CN107874750B | 2020.01.10

Pending

  • Adversarial example detection method based on robustness differences | Fu Song, Zhe Zhao, Guangke Chen | CN112381150A | 2021.02.19
  • Adversarial example detection method based on attack cost | Fu Song, Zhe Zhao, Guangke Chen | CN112381152A | 2021.02.19
  • Audio adversarial example defense based on speech acoustic feature compression | Fu Song, Guangke Chen, Zhe Zhao | CN114242083A | 2022.03.25

Education

  • ShanghaiTech University, Shanghai, Ph.D Student
    Sept 2019 - Now (GPA: 3.91/4.0)
  • South China University of Technology, Guangzhou, Bachelor's Degree
    Sept 2015 - June 2019 (GPA: 3.77/4.0)

Services

Awards & Honors

  • National Scholarship for Ph.D student (top 2%), 2023.10, @ShanghaiTech
  • Merit Student, 2023.11, @ShanghaiTech
  • Merit Student, 2022.12, @ShanghaiTech
  • National Scholarship for Master Student, 2020.11.20, @ShanghaiTech
  • Merit Student, 2020.12.01, @ShanghaiTech
  • National Scholarship, Merit Student, 2018.10, @SCUT
  • Outstanding conclusion of national College Students’ Innovation and Entrepreneurship Training Program, project leader, 2019.05, @SCUT
  • National Encouragement scholarship, Merit Student, 2017.10, @SCUT
  • Enterprise Scholarships, Merit Student, 2016.10, @SCUT