Pin-Yu Chen
       
               Research Staff Member, AI Foundations - Learning Group
    IBM Thomas J. Watson Research Center, NY 
        contact: pinyuchen.tw at gmail.com (primary reviewer account)   
pin-yu.chen at ibm.com
                      Link to my   CV      google scholar profile      academic activities         


I am a Research Staff Member of the AI Foundations - Learning Group, IBM Thomas J. Watson Research Center. My recent research focus has been on adversarial machine learning and studying the robustness of neural networks. My research interest includes graph and network data analytics and their applications to data mining, machine learning, signal processing, and cyber security.
I am open to collaboration with highly motivated researchers!
I received my Ph.D. degree in electrical engineering and computer science (EECS) and M.A. degree in Statistics from the University of Michigan Ann Arbor in 2016, under the supervision of Prof. Alfred Hero.



Research Interests
  • Graph and Network Analytics: spectral graph theory and algorithms, graph signal processing, community detection, graph clustering, event propagation and control in networks, complex network
  • Machine Learning: adversarial machine learning, online and distributed learning, unsupervised and semi-supervised learning on graphs
  • Cyber Security: attack and defense models, action recommendations for network resilience, malware propagation models

Awards and Honors
  • NIPS Best Reviewer Award (2017) <Link>
  • IEEE GlobalSIP 2016 Student Travel Grant
  • ACM KDD 2016 Student Travel Award
  • NSF Graph Signal Processing Workshop Travel Grant (2016) 
  • IEEE Security and Privacy (S&P) Symposium 2016 Student Travel Grant 
  • Outstanding Performance Award at Pacific Northwest National Laboratory (2015)
  • IEEE ICASSP 2015 Signal Processing Society (SPS) Travel Grant
  • IEEE ICASSP 2014 National Science Foundation (NSF) Travel Grant
  • Rackham International Student Fellowship (Chia-Lun Lo Fellowship) (2013-2014) <Link>
  • Member of Tau Beta Pi (TBP) and Phi Kappa Phi (PKP) Honor Society (2013-present)
  • EE:Systems Fellowship, University of Michigan, Ann Arbor (2012-2013)
  • Best Master Thesis Award of GICE, NTU (2011)
  • Second Best Master Thesis Award of Chinese Institute of Electrical Engineering (2011)
  • IEEE GLOBECOM GOLD Best Paper Award (2010) <Link>
  • Elite Scholarship from GICE, NTU (2010-2011)
  • Tokyo Electron Scholarship (2008)
  • Golden Bamboo Scholarship from NCTU (2005)
  • Ranked 1st Place (Full Scores) in Taiwan National College Entrance Exam (2005)

Selected Publications
      Adversarial Machine Learning and Robustness of Neural Networks
      Cyber Security, Network Resilience
      Graph and Network Data Analytics
      Event Propagation Models in Networks
      Optimization for Machine Learning and Signal Processing
      Preprints
      [S1P.-Y. Chen, M.-H. Sung, and S.-M. Cheng, Buffer Occupancy and Delivery Reliability Tradeoffs for Epidemic Routing,” 
      [S2] P.-Y. ChenS. Choudhury, L. Rodriguez, A.  O. Hero, and I. Ray, “Enterprise Cyber Resiliency Against Lateral Movement: A Graph Theoretic Approach,” under review
      [S3P.-Y. Chen and A. O. Hero, “Phase Transitions and a Model Order Selection Criterion for Spectral Graph Clustering,” 
      [S4P.-Y. Chen, C.-C. Tu, P.-S. Ting, Y.-Y. Luo, D. Koutra, and A. O. Hero, “Identifying Influential Links for Event Propagation  on Twitter: A Network of Networks Approach,” in revision
      [S5S. Liu, H. Chen, S. Ronquist, L. Seaman, N. Ceglia, W. Meixner, L. A. Muir, P.-Y. ChenG. Higgins, P. Baldi, S. Smale, A. Hero, and I. Rajapakse, Genome architecture leads a bifurcation in cell identity, under review
      [S6] W. Liu, H. Cooper, M. H. Oh, S. Yeung, P.-Y. Chen, T. Suzumura, and L. Chen, “Learning Graph Topological Features via GAN, 
      [S7] Yash Sharma and Pin-Yu Chen“Attacking the Madry Defense Model with $L_1$-based Adversarial Examples
      [S8] Hongge Chen, Huan Zhang, Pin-Yu Chen, Jinfeng Yi, and Cho-Jui Hsieh, “Show-and-Fool: Crafting Adversarial Examples for Neural Image Captioning
      [S9] Sijia Liu, Pin-Yu Chen, Alfred Hero, and Indika Rajapakse, 
      Dynamic Network Analysis of the 4D Nucleome

      Internship
      • Pacific Northwest National Laboratory (PNNL) - Data Science PhD Intern 
        1. action recommendations for real-time service degradation attacks
        • user segmentation and host hardening against lateral movement attacks

      Fun and Proud Fact: My Erdos number is 4 (through two distinct paths)!! 

          (1. Me -> Alfred Hero -> Wayne Stark -> Robert McEliece -> Paul Erdos)
          (2. Me -> Pai-Shun Ting -> John. P. Hayes -> Frank Harary -> Paul Erdos)