Research Portfolio
My research vision: AI Model Inspector for AI Maintenance -- Make the robustness inspection pipeline for AI models as reliable, standard, and easy, as car maintenance. Check out our AI Maintenance paper and this article for details.
See our survey paper on Holistic Adversarial Robustness of Deep Learning Models
Best paper runner-up award at UAI 2022
Book on "Adversarial Robustness for Machine Learning" published by Elsevier
Adversarial Machine Learning: Attack, Defense, and Robustness Evaluation & Verification
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
Adversarial T-Shirt [ECCV'20]: physical adversarial examples evading person detector
Show-and-Fool [ACL'18]: adversarial examples for neural image captioning systems
Adversarial robustness v.s. classification accuracy tradeoff uncovered from 18 deep ImageNet models + attack transferability analysis between 306 pairs of these networks [ECCV'18]
Adversarial attack on sparse regression (feature identification) [GlobalSIP'18]
CROWN & CNN-Cert & PROVEN & Semantify [NeurIPS'18, AAAI'19, ICML'19, CVPR'20]: Formal (worst-case of probabilistic) and efficient robustness certification of neural networks with general activation functions, popular layer modules, and semantic perturbations
AutoZOOM & ZO-NGD & ZO-ADMM [AAAI'19, ICCV'19, AAAI'20]: query-efficient black-box attacking acceleration via dimensional reduction and advanced zeroth-order optimization techniques (soft-label & hard-label attacks)
Opt Attack & ZO-ADMM & Sign-OPT [ICLR'19, ICCV'19, ICLR'20]: Query-efficient zeroth-order optimization based black-box attack with limited information (decision-based model revealing only top-1 prediction label)
TD detection [ICLR'19]: Detecting adversarial audio inputs using temporal dependency
Structured adversarial attack [ICLR'19]: spatial structure guided adversarial attack and model interpretability
Paraphrasing Attack [SysML'19]: Joint text paraphrasing adversarial attacks at the word and sentence levels and adversarial training
First-order optimization based edge perturbation attack and defense (adversarial training) for graph neural networks [IJCAI'19, ICASSP'20]
HRS [IJCAI'19]: Hierarchical random switching to strengthen the robustness of a trained based model by increasing attacker's costs and improving robustness-accuracy tradeoff
Seq2Sick [AAAI'20]: Generating adversarial examples for sequence-to-sequence models (e.g., machine translation, summarization)
Certified robustness of neural network weight perturbation and its application to robust weight quantization [AAAI'20]
DBA [ICLR'20]: Distributed backdoor attack designed for federated learning; more effective and stealthy
Data leakage in federated learning [NeurIPS'21]: discovery and mitigation of large-scale training data leakage in vertical federated learning
Model sanitization with limited clean data [ICLR'20]: mitigate adversarial effect of a tampered (Trojan) model via mode connectivity
Adversarial robustness transfer and preservation in contrastive learning [NeurIPS'21] and meta learning [ICLR'21]
ZOO (black-box attack via direct model queries)
[AI-Sec'17] https://arxiv.org/abs/1708.03999
EAD (L1 distortion based white-box attack)
[AAAI'18] https://arxiv.org/abs/1709.04114 [ICLR'18 Wksp] https://arxiv.org/abs/1710.10733[ICLR'18 Wksp] https://arxiv.org/abs/1803.09638[DSN'18 Wksp] https://arxiv.org/abs/1805.00310
Show-and-Fool: adversarial examples for neural image captioning systems
[ACL'18] https://arxiv.org/abs/1712.02051
Accuracy v.s. robustness tradeoff of contrastive learning methods
[NuerIPS'21] https://arxiv.org/abs/2111.01124
Physical Adversarial T-Shirt
[ECCV'20] https://arxiv.org/abs/1910.11099
Accuracy v.s. robustness tradeoff of different vision transformers
AutoZOOM: query-efficient black-box adversarial attacking acceleration via dimensional reduction and zeroth-order optimization
Advanced zeroth order optimization = Query-efficient design of adversarial example generation process !
[AAAI'19] https://arxiv.org/abs/1805.11770 [ICLR'19] https://arxiv.org/abs/1807.04457 [ICCV'19] https://arxiv.org/abs/1907.11684
Robustness verification and evaluation for neural nets
Robustness certification for semantic perturbations
[CVPR'20] https://arxiv.org/abs/1912.09533
Adversarial attack on sparse regression
[GlobalSIP'18] https://arxiv.org/abs/1809.08706
HRS: Hierarchical random switching to strengthen the robustness of a trained based model
[IJCAI'19] https://arxiv.org/abs/1908.07116
Detecting adversarial audio inputs using temporal dependency
[ICLR'19] https://arxiv.org/abs/1809.10875
DBA attack exploits the distributed learning nature of federated learning to distribute a global trigger (Trojan) pattern over malicious agents
AI (Deep Learning) x [The Delta!]
AI x [Financial Applications]
A general framework of (deep) reinforcement learning for portfolio management with noisy and heterogeneous alternative data (e.g., stock prices + financial news)
[AAAI'20] https://arxiv.org/abs/2002.05780
AI x [Model IP Protection]
A general and practical framework for model watermark embedding and remote verification, and fingerprinting
[MLSyS'21] https://arxiv.org/abs/2103.03701
[IJCAI'21] https://arxiv.org/abs/2105.07078
AI x [Scientific Discovery]
Machine learning guided molecule optimization with design constraints
[Nature Machine Intelligence] https://arxiv.org/abs/2011.01921
Network Reprogramming: Data-Efficient & Model-Agnostic Transfer Learning
See our survey paper on Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning
Overview of model reprogramming framework: https://arxiv.org/abs/2202.10629
Reprogramming black-box machine learning systems
[ICML'20] https://arxiv.org/abs/2007.08714
Resource efficiency: https://arxiv.org/abs/2202.10629
Reprogramming human voice models for time series classification
[ICML'21] https://arxiv.org/abs/2106.09296
Reprogramming for low-resource speech learning: https://arxiv.org/abs/2110.03894
Reprogramming language models for molecule learning: https://arxiv.org/abs/2012.03460
Community Detection: Theory and Algorithms
Phase transition analysis of community detection under general connectivity models [T-SP, Phy. Rev. E]
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... Performance characterization of community detection
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]
Information propagation in heterogeneous networks
Malware propagation via multiple paths
Network Analytics and Graph Data Mining
FINGER: Fast incremental computation of Von Neumann graph entropy [ICML'19]
Neural network based Bayesian personalized ranking for attributed network embedding [Data Science and Engineering]
Graph Attention Network using High-Order (beyond 1-hop neighborhood) information [IEEE Access]
GAN-based graph generator learned from a single graph [IEEE Access]
Bifurcation analysis of cell reprogramming [ICASSP'18, iScience]
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 [https://arxiv.org/abs/1905.01002]
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 [Phy. Rev. E, J-IoT]
Optimization for Machine Learning and Signal Processing
Mode connectivity in loss landscapes of deep learning [NeurIPS'20]
Survey on Zeroth Order optimization [IEEE Signal Processing Magazine]
Zeroth-order signSGD: faster convergence of zeroth order optimization [ICLR'19]
Non-convex zeroth order stochastic variance reduced algorithm [NeurIPS'18]
Accelerated distributed dual averaging over networked agents [T-SP]
Zeroth-order ADMM: convergence and algorithm [AISTATS'18]
(Last updated in Aug. 2022)