Only tutorials or invited talks are listed. Posters or slides of conference presentations can be found in "Publication" tab
Online Video Presentations
[KDD 2018] Scalable Spectral Clustering Using Random Binning Features
[KDD 2016 Workshop] Incremental Method for Spectral Clustering of Increasing Orders
"Exploring Safety Risks in Large Language Models and Generative AI", Industrial Speakers, PAKDD, May 2024 <LINK>
"Exploring Safety Risks in Large Language Models and Generative AI", IBM Taiwan Solutions Day, March 2024 <LINK> <video>
"An Eye for AI: Towards Scientific Approaches for Evaluating and Improving Robustness and Safety of Foundation Models", Statistical Aspects of Trustworthy Machine Learning workshop, Feb. 2024 <LINK> <video>
"Exploring Safety Risks in Large Language Models and Generative AI", Academia Sinica (可信任AI對話引擎與AI安全論壇), Jan. 2024 <LINK> <video>
"AI Robustness and Safety: What's New for Large Language Models and Generative AI", H&J Global Chair Talks (華仁全球講座), Dec. 2023
"An Eye for AI: Towards Scientific Approaches for Evaluating and Improving Robustness and Safety of Foundation Models", RPI, Nov. 2023
"An Eye for AI: Towards Scientific Approaches for Evaluating and Improving Robustness and Safety of Foundation Models", AAEOY / CIEUSA-GNYC Annual Convention Technical Program, Sep. 2023 <LINK>
"An Eye for AI: Towards Scientific Approaches for Evaluating and Improving Robustness and Safety of Foundation Models", IJCAI Keynote Talk, Aug. 2023 <LINK> <video>
"Exploring Safety Risks in Large Language Models and Generative AI", Shanghai AI Lab, Nov. 2023 <LINK>
"Foundational Robustness of Foundation Models", NIST AI Metrology Colloquia Series, July 203 <LINK> <video>
"How to Backdoor Diffusion Models," Cohere for AI Community Talks, June 2023 <LINK>
"Improving Accuracy-Privacy Tradeoff via Model Reprogramming," Workshop on Information-Theoretic Methods for Trustworthy Machine Learning at Simons Institute, May 2023 <LINK>
"What's Next in Backdoor Attacks and Defenses," ICLR Workshop on Backdoor Attacks and Defenses in Machine Learning (BANDS), May 2023 <LINK> <video>
"Foundational Robustness of Foundation Models," U.S. SEC Quant Seminar, April 2023
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Wayne State University, Mar. 2023 <LINK>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," IEEE CCWC keynote talk, Mar. 2023 <LINK>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Western University, Canada, Feb. 2023
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Taiwan Trustworthy AI Summit, Jan. 2023 <LINK>
"Reprogramming Foundation Models with Limited Resources," Academia Sinica, Jan. 2023 <LINK>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Microsoft Research Asia, Dec. 2022
"Holistic Adversarial Robustness for Deep Learning," Online Asian Machine Learning School (OAMLS), Dec. 2022 <LINK>
"Reprogramming Foundation Models with Limited Resources," ACCV AMLAVS Workshop, Dec. 2022 <LINK>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," 華仁全球講座, Nov. 2022 <video>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Institute for Mathematics and its Applications, University of Minnesota, Oct. 2022 <LINK> <video_AIM>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," C3.ai, Oct. 2022 <LINK> <video_C3>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Commonwealth Scientific and Industrial Research Organisation (CSIRO), Australia, Sep. 2022 <LINK>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Hong Kong Baptist University, Aug 2022 <LINK>
"Reprogramming Foundation Models with Limited Resources," CVPR HCIS Workshop, June 2022 <LINK>
"Reprogramming Foundation Models with Limited Resources," U.S. SEC Quant Seminar, June 2022
"Adversarial Robustness and Reprogramming for Speech and Language Processing: Challenges and New Opportunities", IEEE ICASSP Tutorial, May 2022 <LINK>
"AI Model Inspector: Towards Holistic Adversarial Robustness for Deep Learning," Academia Sinica, April 2022 <LINK>
"Reprogramming Foundation Models with Limited Resources," The Memphis DATA Conference, Mar. 2022 <LINK>
"Holistic Adversarial Robustness of Deep Learning", Industry Expert Session, International Conference on Acoustics, Speech, and Signal Processing, May 2022 <LINK>
"Reprogramming Foundation Models with Limited Resources," 56th Annual Conference on Information Sciences and Systems, Mar. 2022 <LINK>
"Adversarial Machine Learning for Good," AAAI Tutorial, Feb. 2022 <LINK>
"How to make AI hack-proof," IBM Research Video, Dec. 2022 <LINK>
"Reprogramming Large Models with Limited Resources," IBM Research What’s Next Seminar Series, Oct. 2021 <LINK>
"Reprogramming Large Models with Limited Resources," ACM Multimedia Workshop on Adversarial Learning for Multimedia, Oct. 2021 <LINK>
"Adversarial Machine Learning for Good", ICML Workshop on Socially Responsible Machine Learning, July, 2021 <LINK>
"Holistic Adversarial Robustness for Deep Learning," Machine Learning Summer School (MLSS) - Taipei, Aug. 2021 <LINK>
"Practical Adversarial Robustness in Deep Learning: Problems and Solutions," CVPR 2021 Tutorial, June 2021 <LINK>
Panelist on "Software Infrastructure Overview, Existing Tools, and Future Desires", NIST AI Measurement and Evaluation Workshop, June 2021 <LINK>
"Adversarial Robustness of Deep Learning Models," National Yang Ming Chiao Tung University, June 2021 <LINK>
"Practical Backdoor Attacks and Defenses in Machine Learning Systems", Vector Institute, April 2021 <LINK>
"Holistic Adversarial Robustness of Deep Learning Models", George Washington University, April 2021
"Practical Backdoor Attacks and Defenses in Machine Learning Systems", University of Iowa, April 2021
"Holistic Adversarial Robustness", Robust Artificial Intelligence Workshop, Jan. 2021<LINK>
"Practical Backdoor Attacks and Defenses in Machine Learning Systems", Trustworthy ML Seminar, Dec. 2020 <LINK>
"Self-Progressing Robust Training", MLSys workshop on Secure and Resilient Autonomy (SARA), 2020
"Making AI Trustworthy", Taiwan Association for Human Rights (台灣人權促進會), Jan. 2020 <LINK>
"Adversarial Robustness for Deep Learning: Trends and Challenges", CITI, Academia Sinica (中央研究院資訊科技創新研究中心) and National Chiao Tung University (交通大學), Jan. 2020 <LINK_CITI> <LINK_NCTU>
"Making AI Trustworthy", AI Word Conference and Expo, OCT. 2019 <LINK>
"Towards Evaluating and Building Robust Machine Learning Models", Rensselaer Polytechnic Institute (RPI), Oct. 2019
"Recent Progress in Adversarial Robustness of AI Models: Attacks, Defenses, and Certification", University of Nevada, Reno, Oct. 2019
"Recent Progress in Zeroth Order Optimization and Its Applications to Adversarial Robustness in Data Mining and Machine Learning", Tutorial at KDD, Alaska, Aug. 2019 <Outline> <LINK> <slides>
"Adversarial Attack and Defense: An Overview", Advanced Information Security Summer School (AIS3), Taiwan, July 2019 <LINK>
"Recent Progress in Adversarial Robustness of AI Models: Attacks, Defenses, and Certification", IBM Research AI Horizon Network Seminar, April 2019 <LINK>
"Recent Progress in Zeroth Order Optimization and Its Applications to Adversarial Robustness in Deep Learning", IEEE BigData, Seattle, Dec. 2018 <LINK>
"How CLEVER is your neural network? Robustness evaluation against adversarial examples", O’Reilly AI Conference, London, Oct. 2018 & MIT Guest Lecture, Nov. 2018 <LINK> <slides>
“Fantastic Adversarial Examples and Where to Find Them” in Taiwan, National Chung Hsing Univ. (中興大學), Feng Chia Univ. (逢甲大學), National Taiwan Univ. of Science and Technology (台灣科技大學), National Taiwan Univ. (台灣大學), National Chiao Tung Univ. (交通大學), Dec. 2017
"AMOS: An Automated Model Order Selection Algorithm for Spectral Graph Clustering", Annual Machine Learning Symposium, The New York Academy of Science, Mar. 2017 <LINK> <slides>
"Multi-Centrality Graph Spectral Decompositions and Their Application to Cyber Intrusion Detection", Consortium for Verification Technology (CVT) Workshop, Oct. 2016 <slides> <video>
"Graph Data Analytics for Data Science and Cyber Security", National Taiwan University & National Chiao Tung University, Taiwan, Oct. 2016 <LINK>
"Analysis and Actions on Graph Data", Graduate Student Statistical Topics Seminar, University of Michigan Ann Arbor, Sep. 2016 <LINK>
"Phase Transitions and a Model Order Selection Criterion for Spectral Graph Clustering", Graph Signal Processing Workshop, May 2016 <LINK>
"Graph Data Analytics for Data Science and Cyber Security", Research Presentation at King Abdullah University of Science & Technology (KAUST), Apr. 2016 <LINK>
"AMOS: A Model Order Selection Criterion for Spectral Graph Clustering", Michigan Student Symposium for Interdisciplinary Statistical Sciences (MSSISS), University of Michigan, Mar. 2016
"Graph Data Analytics for Data Science and Cyber Security", IBM T. J. Watson Research Center, Mar. 2016 <LINK>
"Graph Data Analytics for Data Science and Cyber Security", Grad-Day presentation, Information Theory and Applications Workshop (ITA), Jan. 2016 <LINK> <video>
"Graph Data Analytics for Data Science and Cyber Security", Research Presentation at Nanyang Technological University (NTU), Jan. 2016
"Analysis and Actions on Graph Data", guest lecture for EECS598: Graph Mining and Exploration at Scale: Methods and Applications, University of Michigan, Dec. 2015 <LINK>
"Embracing Data Science with Graph Mining: Action Recommendations for Cyber Security, Clustering, and Beyond", Engineering Graduate Symposiums (EGS), University of Michigan, Oct. 2015
"Embracing Data Science with Graph Mining: Action Recommendations for Cyber Security, Clustering, and Beyond", From Industrial Statistics to Data Science, a conference in honor of Vijay Nair, Oct. 2015 <LINK>
"Action Recommendations for Cyber Resilience", Pacific Northwest National Laboratory, Aug. 2015 <LINK>
"Universal Phase Transitions of Spectral Algorithms for Community Detection", Annual University of Michigan SIAM Student Conference, University of Michigan, Apr. 2015 <LINK>
"Universal Phase Transitions of Spectral Algorithms for Community Detection", Michigan Student Symposium for Interdisciplinary Statistical Sciences (MSSISS), University of Michigan, Mar. 2015
"Universal Phase Transitions of Spectral Algorithms for Community Detection", Engineering Graduate Symposiums (EGS), University of Michigan, 2014
"Deep and Overlapping Community Detection Using Local Fiedler Vector Centrality", Engineering Graduate Symposiums (EGS), University of Michigan, 2013
"Information Dynamics in Complex Networks", Tutorial at Graduate Institute of Communications Engineering (GICE), National Taiwan University, Aug. 2012