Papers

2024

• AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties
  Xiayan Ji, Anton Xue, Eric Wong, Oleg Sokolsky, Insup Lee
  Neural Information Processing Systems (NeurIPS), 2024
  Source Code on GitHub

• The FIX Benchmark: Extracting Features Interpretable to eXperts
  Helen Jin, Shreya Havaldar, Chaehyeon Kim, Anton Xue, Weiqiu You, Helen Qu, Marco Gatti, Daniel A. Hashimoto, Bhuvnesh Jain, Amin Madani, Masao Sako, Lyle Ungar, Eric Wong
  Site + Blog Post + Source Code on GitHub

• Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
  Anton Xue, Avishree Khare, Rajeev Alur, Surbhi Goel, Eric Wong
  Blog Post + Source Code on GitHub

• Crowd-sourced machine learning prediction of long COVID using data from the National COVID Cohort Collaborative
  Timothy Bergquist, Johanna Loomba, Emily Pfaff, Fangfang Xia, Zixuan Zhao, Yitan Zhu, Elliot Mitchell, Biplab Bhattacharya, Gaurav Shetty, Tamanna Munia, Grant Delong, Adbul Tariq, Zachary Butzin-Dozier, Yunwen Ji, Haodong Li, Jeremy Coyle, Seraphina Shi, Rachael V. Philips, Andrew Mertens, Romain Pirracchio, Mark van der Laan, John M. Colford Jr., Alan Hubbard, Jifan Gao, Guanhua Chen, Neelay Velingker, Ziyang Li, Yinjun Wu, Adam Stein, Jiani Huang, Zongyu Dai, Qi Long, Mayur Naik, John Holmes, Danielle Mowery, Eric Wong, Ravi Parekh, Emily Getzen, Jake Hightower, Jennifer Blase
  eBioMedicine

• Avoiding Copyright Infringement via Machine Unlearning
  Guangyao Dou, Zheyuan Liu, Qing Lyu, Kaize Ding, Eric Wong

• Data-Efficient Learning with Neural Programs
  Alaia Solko-Breslin, Seewon Choi, Ziyang Li, Neelay Velingker, Rajeev Alur, Mayur Naik, Eric Wong
  Neural Information Processing Systems (NeurIPS), 2024
  Blog Post + Source Code on GitHub

• Towards Compositionality in Concept Learning
  Adam Stein, Aaditya Naik, Yinjun Wu, Mayur Naik, Eric Wong
  International Conference on Machine learning (ICML), 2024

• DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
  Yinjun Wu, Mayank Keoliya, Kan Chen, Neelay Velingker, Ziyang Li, Emily J Getzen, Qi Long, Mayur Naik, Ravi B Parikh, Eric Wong
  International Conference on Machine learning (ICML), 2024

• JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
  Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramer, Hamed Hassani, Eric Wong
  Site + Source Code on GitHub

• Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
  Jiabao Ji, Bairu Hou, Alexander Robey, George J. Pappas, Hamed Hassani, Yang Zhang, Eric Wong, Shiyu Chang

• Evaluating Groups of Features via Consistency, Contiguity, and Stability
  Chaehyeon Kim, Weiqiu You, Shreya Havaldar, Eric Wong
  International Conference on Learning Representations (ICLR), 2024 Tiny Papers Track

• SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
  Chongyu Fan, Jiancheng Liu, Yihua Zhang, Dennis Wei, Eric Wong, Sijia Liu
  International Conference on Learning Representations (ICLR), 2024
  Source Code on GitHub

2023

• Initialization Matters for Adversarial Transfer Learning
  Andong Hua, Jindong Gu, Zhiyu Xue, Nicholas Carlini, Eric Wong, Yao Qin
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

• Comparing Styles across Languages
  Shreya Havaldar, Matthew Pressimone, Eric Wong, Lyle Ungar
  Empirical Methods in Natural Language Processing (EMNLP), 2023

• Sum-of-Parts Models: Faithful Attributions for Groups of Features
  Weiqiu You, Helen Qu, Marco Gatti, Bhuvnesh Jain, Eric Wong
  Blog Post + Source Code on GitHub

• Jailbreaking Black Box Large Language Models in Twenty Queries
  Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J. Pappas, Eric Wong
  Blog Post + Source Code on GitHub

• SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
  Alexander Robey, Eric Wong, Hamed Hassani, George J. Pappas
  Blog Post + Source Code on GitHub

• TorchQL: A Programming Framework for Integrity Constraints in Machine Learning
  Aaditya Naik, Adam Stein, Yinjun Wu, Eric Wong, Mayur Naik
  Object-oriented Programming, Systems, Languages, and Applications (OOPSLA), 2024
  Source Code on GitHub

• Stability Guarantees for Feature Attributions with Multiplicative Smoothing
  Anton Xue, Rajeev Alur, Eric Wong
  Neural Information Processing Systems (NeurIPS), 2023
  Blog Post + Source Code on GitHub

• TopEx: Topic-based Explanations for Model Comparison
  Shreya Havaldar, Adam Stein, Eric Wong, Lyle Ungar
  International Conference on Learning Representations (ICLR), 2023 Tiny Papers Track

• Rectifying Group Irregularities in Explanations for Distribution Shift
  Adam Stein, Yinjun Wu, Eric Wong, Mayur Naik

• Do Machine Learning Models Learn Statistical Rules Inferred from Data?
  Aaditya Naik, Yinjun Wu, Mayur Naik, Eric Wong
  International Conference on Machine learning (ICML), 2023
  Blog Post + Source Code on GitHub

• In-context Example Selection with Influences
  Tai Nguyen, Eric Wong
  Blog Post + Source Code on GitHub

• Adversarial Prompting for Black Box Foundation Models
  Natalie Maus*, Patrick Chao*, Eric Wong, Jacob Gardner
  Blog Post + Source Code on GitHub

• Faithful Chain-of-Thought Reasoning
  Qing Lyu*, Shreya Havaldar*, Adam Stein*, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, Chris Callison-Burch
  IJCNLP-AACL, 2023
  Blog Post + Source Code on GitHub

2022

• A data-based perspective on transfer learning
  Saachi Jain*, Hadi Salman*, Alaa Khaddaj*, Eric Wong, Sung Min Park, Aleksander Madry
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
  Blog Post + Source Code on GitHub

• When does bias transfer in transfer learning
  Hadi Salman*, Saachi Jain*, Andrew Ilyas*, Logan Engstrom*, Eric Wong, Aleksander Madry
  Blog Post + Source Code on GitHub

• Missingness bias in model debugging
  Saachi Jain*, Hadi Salman*, Pengchuan Zhang, Vibhav Vineet, Sal Vemprala, Aleksander Madry
  International Conference on Learning Representations (ICLR), 2022
  Blog Post + Source Code on GitHub

2021

• Certified patch robustness via smoothed vision transformers
  Hadi Salman*, Saachi Jain*, Eric Wong*, Aleksander Madry
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
  Blog Post + Source Code on GitHub

• DeepSplit: Scalable verification of deep neural networks via operator splitting
  Shaoru Chen*, Eric Wong*, J. Zico Kolter, Mahyar Fazlyab
  IEEE Open Journal of Control Systems (OJCS), 2022

• Leveraging Sparse Linear Layers for Debuggable Deep Networks
  Eric Wong*, Shibani Santurkar*, Aleksander Madry
  International Conference on Machine learning (ICML), 2021 Long Oral
  Blog Post + Source Code on GitHub

2020

• Learning perturbation sets for robust machine learning
  Eric Wong, J. Zico Kolter
  International Conference on Learning Representations (ICLR), 2021
  Blog Post + Source Code on GitHub

• Overfitting in adversarially robust deep learning
  Leslie Rice*, Eric Wong*, J. Zico Kolter
  International Conference on Machine learning (ICML), 2020
  Source Code on GitHub

• Neural network virtual sensors for fuel injection quantities with provable performance specifications
  Eric Wong, Tim Schneider, Joerg Schmitt, Frank R. Schmidt, J. Zico Kolter
  IEEE Intelligent Vehicles Syimposium (IV), 2020

• Fast is better than free: revisiting adversarial training
  Eric Wong*, Leslie Rice*, J. Zico Kolter
  International Conference on Learning Representations (ICLR), 2020

2019

• Adversarial robustness against the union of multiple perturbation models
  Pratyush Maini, Eric Wong, J. Zico Kolter
  International Conference on Machine learning (ICML), 2020
  Source Code on GitHub

• Wasserstein adversarial examples
  Eric Wong, Frank R. Schmidt, J. Zico Kolter
  International Conference on Machine Learning (ICML), 2019

2018

• Scaling provable adversarial defenses
  Eric Wong, Frank R. Schmidt, Jan Hendrik Metzen, J. Zico Kolter
  In Neural Information Processing Systems (NeurIPS), 2018
  Source Code on GitHub

2017

• Provable defenses against adversarial examples via the convex outer adversarial polytope
  Eric Wong, J. Zico Kolter
  International Conference on Machine Learning (ICML), 2018; Best defense paper at NIPS 2017 ML & Security Workshop
  Blog Post + Source Code on GitHub

• A Semismooth Newton Method for Fast, Generic Convex Programming
  Alnur Ali*, Eric Wong*, J. Zico Kolter
  International Conference on Machine Learning (ICML), 2017
  Source Code on GitHub

2015

• An SVD and Derivative Kernel Approach to Learning from Geometric Data
  Eric Wong, J. Zico Kolter
  Conference on Artificial Intelligence (AAAI), 2015

Other

My PhD thesis can be found here.