YUCHEN
profile photo

Yuchen Yang

I am a fourth-year Ph.D. student in Department of Computer Science at Johns Hopkins University, where I'm honored to be advised by Dr. Yinzhi Cao. I'm also working closely with Dr. Neil Zhenqiang Gong from Duke University. Before that, I received my M.S. in Security Informatics at Johns Hopkins University and my B.E. in Software Engineer at Shandong University.

My research interests focus on security and privacy issues in artificial intelligence (AI) and machine learning (ML). Currently, I'm working on the safety issue of AI generative content, e.g., evaluating the robustness of text-to-image generative models in preventing harmful generation. I'm also working on making privacy-preserving ML more accurate, e.g., accurate federated learning and differential privacy.

Email: yc [dot] yang [at] jhu [dot] edu  /  CV  /  Google Scholar  /  GitHub

News

  • 05/2024, Our paper on mitigating unsafe generation from text-to-image models has been accepted by CCS 2024.
  • 11/2023, Our paper on jailbreaking text-to-image models has been accepted by S&P 2024.
  • 10/2023, I will relocate to San Jose for a three-month internship at Honda Research Institute, see you there!
  • Publications

  • SneakyPrompt: Jailbreaking Text-to-image Generative Models
    Yuchen Yang, Bo Hui, Haolin Yuan, Neil Zhenqiang Gong, Yinzhi Cao
    In the Proceedings of the IEEE Symposium on Security and Privacy (S&P), 2024
    Reported by MIT Technology Review and IEEE Spectrum
    paper | code
  • SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
    Xinfeng Li, Yuchen Yang, Jiangyi Deng, Chen Yan, Yanjiao Chen, Xiaoyu Ji, Wenyuan Xu
    To appear in the Proceedings of The ACM Conference on Computer and Communications Security (CCS), 2024
    paper
  • PrivateFL: Accurate, Differentially Private Federated Learning via Personalized Data Transformation
    Yuchen Yang*, Bo Hui*, Haolin Yuan*, Neil Zhenqiang Gong, Yinzhi Cao
    In the Proceedings of USENIX Security Symposium, 2023
    Artifact Badges: Artifacts Available, Artifacts Functional, Results Reproduced
    (* Equal Contributions)
    paper | code
  • Fortifying Federated Learning against Membership Inference Attacks via Client-level Input Perturbation
    Yuchen Yang, Haolin Yuan, Bo Hui, Neil Zhenqiang Gong, Yinzhi Cao
    In the Proceedings of IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) 2023
    paper | code
  • Addressing Heterogeneity in Federated Learning via Distributional Transformation
    Haolin Yuan*, Bo Hui*, Yuchen Yang*, Philippe Burlina, Neil Zhenqiang Gong, Yinzhi Cao
    In the Proceedings of European Conference on Computer Vision (ECCV), 2022
    (* Equal Contributions)
    paper | code
  • Practical Blind Membership Inference Attack via Differential Comparisons
    Bo Hui*, Yuchen Yang*, Haolin Yuan*, Philippe Burlina, Neil Zhenqiang Gong, Yinzhi Cao
    In the Proceedings of Network & Distributed System Security Symposium (NDSS), 2021
    (* Equal Contributions)
    paper | slides| code

  • Experiences

  • Research Assistant, at Johns Hopkins University, 2020.3 - Present

  • Student Associate, at Honda Research Institute, 2023.10 - 2024.2

  • Teaching Assistant, at Johns Hopkins University, 2020.9 - 2020.12, 2022.9 - 2022.12

  • Research Assistant, at Chinese Academy of Sciences, 2018.6 - 2018.9

  • Services

  • IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) 2024, Artifact Evaluation Committee

  • ACM ASIA Conference on Computer and Communications Security (ASIACCS), 2024, External reviewer

  • USENIX Security Symposium 2023, External reviewer

  • The ACM Conference on Computer and Communications Security (CCS) 2022, External reviewer

  • IEEE Computer Security Foundations Symposium (CSF) 2022, External reviewer

  • IEEE International Conference on Distributed Computing Systems (ICDCS) 2022, External reviewer

  • More about me

    I'm glad to introduce my cat Go-Wha, pronunciation in Chinese means PUPPY since he acts like a puppy all the time. Funniest and happiest cat I'v ever seen! You will know it with one click :)

    What's more? How about a cheerleader (former), a kayak learner (recent), and a hotpot lover (forever)!

    Template