Research Portfolio

Adversarial Machine Learning: Attack, Defense, and Robustness Evaluation

    • Adversarial robustness v.s. classification accuracy tradeoff learned from 18 deep ImageNet models + attack transferability analysis between 306 pairs of these networks [ECCV'18]
    • Show-and-Fool [ACL'18]: adversarial examples for neural image captioning systems
    • ZOO [AI-Sec'17]: powerful black-box attack to neural networks - nearly the same performance as white-box attacks
    • EAD [AAAI'18, two ICLR'18 Wksp, DSN'18 Wksp]: crafting L1 norm based adversarial examples - better attack transferability; weakened several defenses and adversary analysis
    • CLEVER [ICLR'18, GlobalSIP'18]: attack-agnostic network robustness measure - estimating certified attack lower bounds

ZOO (black-box attack)

EAD (L1 based white-box attack)


CLEVER robustness score for neural nets

Accuracy v.s. robustness tradeoff

Community Detection: Theory and Algorithms

    • Phase transition analysis of community detection under general connectivity models [T-SP, PRE]
    • AMOS & MIMOSA: theory-driven automated community detection algorithms for single-layer [T-SP] and multi-layer graphs [T-SIPN]
    • Deep (core) community detection [T-SP]
    • SGC-GEN: pseudo-supervised community detection meta algorithm [ICDM'17]

To be detectable, or not to be...

Communication detection in multi-layer networks

Network Analytics and Graph Data Mining

    • Scalable end-to-end spectral clustering using random features [KDD'18]
    • Structural feature extraction from a single graph or a graph sequence [ICASSP'16]
    • Anomaly detection based on graph connectivity

Event Propagation and Control in Networks

    • Modeling malware propagation in heterogeneous networks [Comm. Mag, Comm. Lett., J-IoT, T-CB, GLOBECOM'10]
    • Event propagation control via node and edge patching in communication networks [Comm. Mag.]
    • Identifying influential links on Twitter networks using network of networks model [T-SIPN]

Heterogeneous networks

Malware propagation

Tweet propagation and user language fields

Network Resilience

    • LFVC: effective centrality measure based attack for network disruption [ICASSP'14, Comm. Mag.]
    • Sequential and game-theoretic information fusion for defending connectivity attacks [PRE, J-IoT]


    • Accelerated distributed dual averaging over networked agents [T-SP]
    • Zeroth-order ADMM: convergence and algorithm [AISTATS'18]

(Last updated in Aug. 2018)