Pin-Yu Chen (陳品諭)

Research Staff Member, AI Foundations - Learning Group & MIT-IBM AI Lab

IBM Research AI, IBM Thomas J. Watson Research Center, NY

Link to my Twitter Google scholar profile CV Academic activities

Contact: pinyuchen.tw at gmail.com (primary reviewer account) , pin-yu.chen at ibm.com

- I am a Research Staff Member of the AI Foundations - Learning Group & MIT-IBM AI Lab, 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 and M.A. degree in Statistics from the University of Michigan Ann Arbor in 2016, under the supervision of Prof. Alfred Hero.

- Editorial board: PLOS ONE, IEEE J-IOT (Guest)

- Selected conference reviewers: NIPS, ICML, AAAI, ICLR, ICDM, INFOCOM, GLOBECOM, ICC, WCNC, ACC, ICASSP, ICME

- Selected journal reviewers: IEEE T-SP, J-STSP, T-SIPN, T-KDE, T-PAMI, J-SAC, ToN, TWC, CL, T-PDS, WCM, WCL, J-IoT, SPL, T-CNS, ACCESS, J-ETCAS; PLOS ONE

- News coverage of my research:

RecentEvents

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 Papers

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

[S1] Pin-Yu Chen, Lingfei Wu, Sijia Liu, and Indika Rajapakse, “Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications,”

[S2] P.-Y. Chen, S. Choudhury, L. Rodriguez, A. O. Hero, and I. Ray, “Enterprise Cyber Resiliency Against Lateral Movement: A Graph Theoretic Approach,” under review

[S3] Sijia Liu, Bhavya Kailkhura, Pin-Yu Chen, Pai-Shun Ting, Shiyu Chang, and Lisa Amini, “Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization,”

[S5] S. Liu, H. Chen, S. Ronquist, L. Seaman, N. Ceglia, W. Meixner, L. A. Muir, P.-Y. Chen, G. 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] Chun-Chen Tu*, Paishun Ting*, Pin-Yu Chen*, Sijia Liu, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh, and Shin-Ming Cheng, “AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks,” (*equal contribution) <AutoZOOM_code>

[S8] Sijia Liu, Pin-Yu Chen, Alfred Hero, and Indika Rajapakse, “Dynamic Network Analysis of the 4D Nucleome”

[S9] Amit Dhurandhar*, Pin-Yu Chen*, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, and Payel Das, “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives” (*equal contribution) <CEM_code> <Forbes_coverage><The_Weekly_Observer_coverage>

[S10] Minhao Cheng, Jinfeng Yi, Huan Zhang, Pin-Yu Chen, and Cho-Jui Hsieh, “Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples” <Seq2Sick_code>

[S11] Yash Sharma and Pin-Yu Chen, “Bypassing Feature Squeezing by Increasing Adversary Strength”

[S12] Zhuolin Yang, Bo Li, Pin-Yu Chen, and Dawn Song, “Towards Mitigating Audio Adversarial Examples”

[S13] Minhao Cheng, Thong Le, Pin-Yu Chen, Jinfeng Yi, Huan Zhang, and Cho-Jui Hsieh, “Query-Efficient Hard-label Black-box Attack: An Optimization-based Approach” <Code>

U.S. Patents

[PA1] System and Methods for Automated Detection, Reasoning, and Recommendations for Resilient Cyber Systems

Internship

  • Pacific Northwest National Laboratory (PNNL) - Data Science PhD Intern
    • 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)