Khoa D. Doan

I am a Researcher in the Cognitive Computing Lab at Baidu Research working with Dr. Ping Li on generative modeling and its practical applications (e.g., Information Retrieval and AI Security). Previously, I was at Virginia Tech/Sanghani Center for Artificial Intelligence & Data Analytics (Prof. Chandan K. Reddy) ⟵ Criteo AI Lab (Dr. Sathiya Keerthi Selvaraj and Dr. Fengjiao Wang) ⟵ UMCP/NASA Goddard Space Flight Center. More about me HERE and my professional/academic services HERE.

I’m looking for motivated research interns/assistants in Vietnam (and potentially other Asian countries), working on Robust ML (e.g., adversarial robustness, backdoor/poisoning attacks, & OOD/generalization robustness), Generative Models (e.g., energy-based generative models and diffusion models), and Low-resource NLP (e.g., translation & summarization). Please fill out this form if you are interested!

Research Interests

My research seeks answers to the following question: How to make ML models simpler & reliable to use in constrained settings? I am interested in developing computational frameworks that enable existing complex/deep models to be more suitable for practical uses. I focus on improving the following aspects of existing models: (i) training/inference, (ii) realistic assumptions, (iii) algorithmic robustness, and (iv) efficiency in constrained settings. Most of my ML/AI solutions center around generative-based approaches that have low computational complexity and require less human effort. More about my research interests HERE.

news

[04/2023]	One paper accepted to SIGIR’2023 on real-time ranking with non-metric/non-linear ranking functions (yes, Neural Networks!)
[02/2023]	Gave a talk at Lucy Family Institute for Data and Society, University of Notre Dame on Toward Practical Machine Learning Applications in Constrained Settings.
[02/2023]	Will serve as Invited PC for FAccT, ICML, and ICCV 2023.
[01/2023]	Will serve on the Editorial Board of Springer’s Discover Data.
[12/2022]	Recognized as Top Reviewer at NeurIPS 2022.
[11/2022]	One paper accepted to AAAI’2023 on a novel/ONLINE defense against Backdoor Attacks on ViTs.
[11/2022]	Will serve as Invited PC for CVPR 2023.
[09/2022]	One paper accepted to NeurIPS’2022 on a new threat of Backdoor Attacks.
[09/2022]	One paper accepted to ACCV’2022 on EBM/Retrieval.
[07/2022]	Will serve as Invited PC for AAAI and ICLR 2023.
[04/2022]	Gave a talk on Deep Retrieval Model at VinAI Research, Vietnam
[03/2022]	Will serve as Invited PC for NeurIPS 2022.
[03/2022]	One paper accepted to CVPR’2022 on Generative Model/Image Hashing.
[03/2022]	Will serve as Invited PC for ECCV 2022.
[12/2021]	Will serve as Invited PC for ICML 2022.

selected publications [full list]

AAAI Defending backdoor attacks on vision transformer via patch processing

Doan, Khoa D, Lao, Yingjie, and Li, Ping

In AAAI Conference on Artificial Intelligence 2023

Bib
@inproceedings{doan2023bdvits, bibtex_show = {true}, abbr = {AAAI}, title = {Defending backdoor attacks on vision transformer via patch processing}, author = {Doan, Khoa D and Lao, Yingjie and Li, Ping}, booktitle = {AAAI Conference on Artificial Intelligence}, year = {2023}, teaser = {doan2023bdvits.png}, selected = {true} }
NeurIPS Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class

Doan, Khoa D, Lao, Yingjie, and Li, Ping

In Thirty-Sixth Conference on Neural Information Processing Systems 2022

Bib
@inproceedings{doan2022marksman, bibtex_show = {true}, abbr = {NeurIPS}, title = {Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class}, author = {Doan, Khoa D and Lao, Yingjie and Li, Ping}, booktitle = {Thirty-Sixth Conference on Neural Information Processing Systems}, year = {2022}, teaser = {doan2022marksman.png}, selected = {true} }
CVPR One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching

Doan, Khoa D, Yang, Peng, and Li, Ping

In Conference on Computer Vision and Pattern Recognition 2022

Bib PDF Code Slides
@inproceedings{doan2022hswd, bibtex_show = {true}, abbr = {CVPR}, title = {One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional Matching}, author = {Doan, Khoa D and Yang, Peng and Li, Ping}, booktitle = {Conference on Computer Vision and Pattern Recognition}, year = {2022}, slides = {doan2022hswd-slides.pdf}, code = {https://github.com/khoadoan106/single_loss_quantization}, pdf = {https://openreview.net/pdf?id=uaqweIZ-9_k}, teaser = {doan2022hswd.png}, selected = {true} }

NeurIPS Backdoor Attack with Imperceptible Input and Latent Modification

Doan, Khoa D, Lao, Yingjie, and Li, Ping

In Thirty-Fifth Conference on Neural Information Processing Systems 2021

Bib PDF VIDEO Code Slides

@inproceedings{doan2021wb,
  bibtex_show = {true},
  abbr = {NeurIPS},
  title = {Backdoor Attack with Imperceptible Input and Latent Modification},
  author = {Doan, Khoa D and Lao, Yingjie and Li, Ping},
  booktitle = {Thirty-Fifth Conference on Neural Information Processing Systems},
  year = {2021},
  pdf = {https://proceedings.neurips.cc/paper/2021/file/9d99197e2ebf03fc388d09f1e94af89b-Paper.pdf},
  code = {https://github.com/khoadoan106/backdoor_attacks},
  video = {https://recorder-v3.slideslive.com/?share=51522&s=8af881c0-56e8-451e-865f-adb1e90e5471},
  slides = {doan2021wb-slides.pdf},
  teaser = {doan2021wb.png},
  selected = {true}
}

ICCV LIRA: Learnable, Imperceptible and Robust Backdoor Attacks

Doan, Khoa D, Lao, Yingjie, Zhao, Weijie, and Li, Ping

In International Conference on Computer Vision 2021

Abs Bib PDF Code Poster Slides

Recently, machine learning models have demonstrated to be vulnerable to backdoor attacks, primarily due to the lack of transparency in black-box models such as deep neural networks. A third-party model can be poisoned such that it works adequately in normal conditions but behaves maliciously on samples with specific trigger patterns. However, the trigger injection function is manually defined in most existing backdoor attack methods, e.g., placing a small patch of pixels on an image or slightly deforming the image before poisoning the model. This results in a two-stage approach with a sub-optimal attack success rate and a lack of complete stealthiness under human inspection. In this paper, we propose a novel and stealthy backdoor attack framework, LIRA, which jointly learns the optimal, stealthy trigger injection function and poisons the model. We formulate such an objective as a non-convex, constrained optimization problem. Under this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on the poisoned data. Then, we solve this challenging optimization problem with an efficient, two-stage stochastic optimization procedure. Finally, the proposed attack framework achieves 100% success rates in several benchmark datasets, including MNIST, CIFAR10, GTSRB, and T-ImageNet, while simultaneously bypassing existing backdoor defense methods and human inspection.
@inproceedings{doan2021lira, bibtex_show = {true}, abbr = {ICCV}, title = {LIRA: Learnable, Imperceptible and Robust Backdoor Attacks}, author = {Doan, Khoa D and Lao, Yingjie and Zhao, Weijie and Li, Ping}, booktitle = {International Conference on Computer Vision}, code = {https://github.com/khoadoan106/backdoor_attacks}, slides = {https://github.com/sunbelbd/invisible_backdoor_attacks/raw/master/resources/ICCV2021-LIRA-Slides.pdf}, poster = {https://github.com/sunbelbd/invisible_backdoor_attacks/raw/master/resources/ICCV2021-LIRA-Poster.pdf}, pdf = {https://openaccess.thecvf.com/content/ICCV2021/papers/Doan_LIRA_Learnable_Imperceptible_and_Robust_Backdoor_Attacks_ICCV_2021_paper.pdf}, year = {2021}, teaser = {doan2021lira.png}, selected = {true} }
SIGIR Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings

Doan, Khoa D, Manchanda, Saurav, Mahapatra, Suchismit, and Reddy, Chandan K

In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval 2021

Abs Bib PDF VIDEO Code Slides

Computing graph similarity is an important task in many graph-related applications such as retrieval in graph databases or graph clustering. While numerous measures have been proposed to capture the similarity between a pair of graphs, Graph Edit Distance (GED) and Maximum Common Subgraphs (MCS) are the two widely used measures in practice. GED and MCS are domain-agnostic measures of structural similarity between the graphs and define the similarity as a function of pairwise alignment of different entities (such as nodes, edges, and subgraphs) in the two graphs. The explicit explainability offered by the pairwise alignment provides transparency and justification of the similarity score, thus, GED and MCS have important practical applications. However, their exact computations are known to be NP-hard. While recently proposed neural-network based approximations have been shown to accurately compute these similarity scores, they have limited ability in providing comprehensive explanations compared to classical combinatorial algorithms, e.g., Beam search. This paper aims at efficiently approximating these domain-agnostic similarity measures through a neural network, and simultaneously learning the alignments (i.e., explanations) similar to those of classical intractable methods. Specifically, we formulate the similarity between a pair of graphs as the minimal "transformation" cost from one graph to another in the learnable node-embedding space. We show that, if node embedding is able to capture its neighborhood context closely, our proposed similarity function closely approximates both the alignment and the similarity score of classical methods. Furthermore, we also propose an efficient differentiable computation of our proposed objective for model training. Empirically, we demonstrate that the proposed method achieves up to 50%-100% reduction in the Mean Squared Error for the graph similarity approximation task and up to 20% improvement in the retrieval evaluation metrics for the graph retrieval task. The source code is available at https://github.com/khoadoan/GraphOTSim.
@inproceedings{doan2021interpretable, bibtex_show = {true}, abbr = {SIGIR}, url = {https://doi.org/10.1145/3404835.3462960}, code = {https://github.com/khoadoan/GraphOTSim}, pdf = {doan2021interpretable.pdf}, slides = {https://github.com/khoadoan/GraphOTSim/raw/main/resources/SIGIR21-fp0937-slides.pdf}, video = {https://www.youtube.com/watch?v=IWxxsuFPsgs&t=1s}, teaser = {doan2021interpretable.png}, selected = {true}, author = {Doan, Khoa D and Manchanda, Saurav and Mahapatra, Suchismit and Reddy, Chandan K}, title = {Interpretable Graph Similarity Computation via Differentiable Optimal Alignment of Node Embeddings}, year = {2021}, isbn = {9781450380379}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, doi = {10.1145/3404835.3462960}, booktitle = {Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval}, pages = {665–674}, numpages = {10}, keywords = {similarity search, model interpretability, graph similarity, GCN}, location = {Virtual Event, Canada}, series = {SIGIR '21} }
WWW Efficient Implicit Unsupervised Text Hashing Using Adversarial Autoencoder

Doan, Khoa D, and Reddy, Chandan K

In Proceedings of The Web Conference 2020

Abs Bib HTML PDF

Searching for documents with semantically similar content is a fundamental problem in the information retrieval domain with various challenges, primarily, in terms of efficiency and effectiveness. Despite the promise of modeling structured dependencies in documents, several existing text hashing methods lack an efficient mechanism to incorporate such vital information. Additionally, the desired characteristics of an ideal hash function, such as robustness to noise, low quantization error and bit balance/uncorrelation, are not effectively learned with existing methods. This is because of the requirement to either tune additional hyper-parameters or optimize these heuristically and explicitly constructed cost functions. In this paper, we propose a Denoising Adversarial Binary Autoencoder (DABA) model which presents a novel representation learning framework that captures structured representation of text documents in the learned hash function. Also, adversarial training provides an alternative direction to implicitly learn a hash function that captures all the desired characteristics of an ideal hash function. Essentially, DABA adopts a novel single-optimization adversarial training procedure that minimizes the Wasserstein distance in its primal domain to regularize the encoder’s output of either a recurrent neural network or a convolutional autoencoder. We empirically demonstrate the effectiveness of our proposed method in capturing the intrinsic semantic manifold of the related documents. The proposed method outperforms the current state-of-the-art shallow and deep unsupervised hashing methods for the document retrieval task on several prominent document collections.
@inproceedings{doan2020efficient, bibtex_show = {true}, abbr = {WWW}, url = {https://doi.org/10.1145/3366423.3380150}, html = {https://dl.acm.org/doi/abs/10.1145/3366423.3380150}, pdf = {https://people.cs.vt.edu/~reddy/papers/WWW20a.pdf}, teaser = {doan2020efficient.png}, selected = {true}, author = {Doan, Khoa D and Reddy, Chandan K}, title = {Efficient Implicit Unsupervised Text Hashing Using Adversarial Autoencoder}, year = {2020}, isbn = {9781450370233}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, doi = {10.1145/3366423.3380150}, booktitle = {Proceedings of The Web Conference}, pages = {684–694}, numpages = {11}, keywords = {autoencoder, Hashing, adversarial training, deep learning.}, location = {Taipei, Taiwan}, series = {WWW '20} }
arXiv Gradient boosting neural networks: Grownet

Badirli, Sarkhan, Liu, Xuanqing, Xing, Zhengming, Bhowmik, Avradeep, Doan, Khoa D, and Selvaraj, Sathiya K

arXiv preprint arXiv:2002.07971 2020

Abs Bib PDF Code

A novel gradient boosting framework is proposed where shallow neural networks are employed as ``weak learners''. General loss functions are considered under this unified framework with specific examples presented for classification, regression, and learning to rank. A fully corrective step is incorporated to remedy the pitfall of greedy function approximation of classic gradient boosting decision tree. The proposed model rendered outperforming results against state-of-the-art boosting methods in all three tasks on multiple datasets. An ablation study is performed to shed light on the effect of each model components and model hyperparameters.
@article{badirli2020gradient, bibtex_show = {true}, abbr = {arXiv}, url = {https://arxiv.org/abs/2002.07971}, code = {https://github.com/sbadirli/GrowNet}, pdf = {https://arxiv.org/pdf/2002.07971.pdf}, teaser = {badirli2020gradient.png}, selected = {true}, title = {Gradient boosting neural networks: Grownet}, author = {Badirli, Sarkhan and Liu, Xuanqing and Xing, Zhengming and Bhowmik, Avradeep and Doan, Khoa D and Selvaraj, Sathiya K}, journal = {arXiv preprint arXiv:2002.07971}, year = {2020} }
CIKM Adversarial Factorization Autoencoder for Look-Alike Modeling

Doan, Khoa D, Yadav, Pranjul, and Reddy, Chandan K

In Proceedings of the 28th ACM International Conference on Information and Knowledge Management 2019

Abs Bib PDF

Digital advertising is performed in multiple ways, for e.g., contextual, display-based and search-based advertising. Across these avenues, the primary goal of the advertiser is to maximize the return on investment. To realize this, the advertiser often aims to target the advertisements towards a targeted set of audience as this set has a high likelihood to respond positively towards the advertisements. One such form of tailored and personalized, targeted advertising is known as look-alike modeling, where the advertiser provides a set of seed users and expects the machine learning model to identify a new set of users such that the newly identified set is similar to the seed-set with respect to the online purchasing activity. Existing look-alike modeling techniques (i.e., similarity-based and regression-based) suffer from serious limitations due to the implicit constraints induced during modeling. In addition, the high-dimensional and sparse nature of the advertising data increases the complexity. To overcome these limitations, in this paper, we propose a novel Adversarial Factorization Autoencoder that can efficiently learn a binary mapping from sparse, high-dimensional data to a binary address space through the use of an adversarial training procedure. We demonstrate the effectiveness of our proposed approach on a dataset obtained from a real-world setting and also systematically compare the performance of our proposed approach with existing look-alike modeling baselines.
@inproceedings{doan2019adversarial, bibtex_show = {true}, abbr = {CIKM}, pdf = {https://dmkd.cs.vt.edu/papers/CIKM19.pdf}, teaser = {doan2019adversarial.png}, selected = {true}, author = {Doan, Khoa D and Yadav, Pranjul and Reddy, Chandan K}, title = {Adversarial Factorization Autoencoder for Look-Alike Modeling}, year = {2019}, isbn = {9781450369763}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3357384.3357807}, doi = {10.1145/3357384.3357807}, booktitle = {Proceedings of the 28th ACM International Conference on Information and Knowledge Management}, pages = {2803–2812}, numpages = {10}, keywords = {deep learning, autoencoder, hashing, factorization, adversarial training, look-alike modeling}, location = {Beijing, China}, series = {CIKM '19} }