2024
- Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs [arXiv]
Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin
Annual Meeting of the Association for Computational Linguistics (ACL), 2024
- How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs [arXiv]
Yi Zeng, Hongpeng Lin, Jingwen Zhang, Diyi Yang, Ruoxi Jia, Weiyan Shi
Annual Meeting of the Association for Computational Linguistics (ACL), 2024
- Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits [arXiv]
Jiachen T. Wang, Tianji Yang, James Zou, Yongchan Kwon, Ruoxi Jia
International Conference on Machine Learning (ICML), 2024
Oral presentation
- RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content [arXiv]
Zhuowen Yuan, Zidi Xiong, Yi Zeng, Ning Yu, Ruoxi Jia, Dawn Song, Bo Li
International Conference on Machine Learning (ICML), 2024
- A Safe Harbor for AI Evaluation and Red Teaming [arXiv]
Shayne Longpre, Sayash Kapoor, Kevin Klyman, Ashwin Ramaswami, Rishi Bommasani, Borhane Blili-Hamelin, Yangsibo Huang, Aviya Skowron, Zheng-Xin Yong, Suhas Kotha, Yi Zeng, Weiyan Shi, Xianjun Yang, Reid Southen, Alexander Robey, Patrick Chao, Diyi Yang, Ruoxi Jia, Daniel Kang, Sandy Pentland, Arvind Narayanan, Percy Liang, Peter Henderson
International Conference on Machine Learning (ICML), 2024
Oral presentation
- Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models [arXiv]
Bilgehan Sel, Ahmad Al-Tawaha, Vanshaj Khattar, Ruoxi Jia, Ming Jin
International Conference on Machine Learning (ICML), 2024
- Learning to Rank for Active Learning via Multi-Task Bilevel Optimization [arXiv]
Zixin Ding, Si Chen, Ruoxi Jia, Yuxin Chen
Conference on Uncertainty in Artificial Intelligence (UAI), 2024
- The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes [arXiv]
Myeongseob Ko, Feiyang Kang, Weiyan Shi, Ming Jin, Zhou Yu, Ruoxi Jia
Conference on Computer Vision and Pattern Recognition (CVPR), 2024
- Efficient Data Valuation for Weighted Nearest Neighbor Algorithms [arXiv]
Jiachen Wang, Prateek Mittal, Ruoxi Jia
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
Oral presentation
- Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs [openreivew]
Feiyang Kang, Hoang Anh Just*, Yifan Sun*, Himanshu Jahagirdar*, Yuanzhi Zhang, Rongxing Du, Anit Kumar Sahu, Ruoxi Jia
International Conference on Learning Representations (ICLR), 2024
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! [openreivew]
Xiangyu Qi*, Yi Zeng*, Tinghao Xie*, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, Peter Henderson
International Conference on Learning Representations (ICLR), 2024
Oral presentation
Featured in the New York Times
2023
- Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources [arXiv]
Feiyang Kang*, Hoang Anh Just*, Anit Kumar Sahu, Ruoxi Jia
Conference on Neural Information Processing Systems (NeurIPS), 2023
Adopted by Amazon for data selection
- Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation [arXiv]
Jiachen T. Wang, Yuqing Zhu, Yu-Xiang Wang, Ruoxi Jia, Prateek Mittal
Conference on Neural Information Processing Systems (NeurIPS), 2023
Spotlight presentation
- A Randomized Approach for Tight Privacy Accounting [arXiv]
Jiachen T. Wang, Saeed Mahloujifar, Tong Wu, Ruoxi Jia, Prateek Mittal
Conference on Neural Information Processing Systems (NeurIPS), 2023
- Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study
Myeongseob Ko, Ming Jin, Chenguang Wang, Ruoxi Jia
International Conference on Computer Vision (ICCV), 2023
- One-Round Active Learning through Data Utility Learning and Proxy Models [openreview]
Jiachen T. Wang, Si Chen, Ruoxi Jia
Transactions on Machine Learning Research, 2023
- Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion [openreview]
Si Chen, Yi Zeng, Won Park, Jiachen T. Wang, Xun Chen, Lingjuan Lyu, Zhuoqing Mao, Ruoxi Jia
Transactions on Machine Learning Research, 2023
- PrivMon: A Stream-Based System for Real-Time Privacy Attack Detection for Machine Learning Models
Myeongseob Ko*, Xinyu Yang*, Zhengjie Ji, Hoang Anh Just, Peng Gao, Anoop Kumar, Ruoxi Jia
International Symposium on Research in Attacks, Intrusions, and Defenses (RAID), 2023
- ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms [arXiv]
Minzhou Pan*, Yi Zeng*, Lingjuan Lyu, Xue Lin, Ruoxi Jia
USENIX Security, 2023
- Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information [arXiv]
Yi Zeng*, Minzhou Pan*, Hoang Anh Just, Lingjuan Lyu, Meikang Qiu, Ruoxi Jia
ACM Conference on Computer and Communications Security (CCS), 2023
- 2D-Shapley: A Framework for Fragmented Data Valuation [arXiv]
Liu Zhihong*, Hoang Anh Just*, Xiangyu Chang, Xi Chen, Ruoxi Jia
International Conference on Machine Learning (ICML), 2023
- Revisiting Data-Free Knowledge Distillation with Poisoned Teachers [arXiv]
Junyuan Hong*, Yi Zeng*, Shuyang Yu, Lingjuan Lyu, Ruoxi Jia, Jiayu Zhou
International Conference on Machine Learning (ICML), 2023
- How to Sift Out a Clean Data Subset in the Presence of Data Poisoning? [pdf]
Yi Zeng*, Minzhou Pan*, Himanshu Jahagirdar, Ming Jin, Lingjuan Lyu, Ruoxi Jia
USENIX Security, 2023
- Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold
Bilgehan Sel, Ahmad Al-Tawaha, Yuhao Ding, Ruoxi Jia, Bo Ji, Javad Lavaei, Ming Jin
Learning for Dynamics and Control Conference (L4DC), 2023
Oral presentation
- LAVA: Data Valuation without Pre-Specified Learning Algorithms [openreview]
Hoang Anh Just*, Feiyang Kang*, Jiachen T. Wang, Yi Zeng, Myeongseob Ko, Ming Jin, Ruoxi Jia
International Conference on Learning Representations (ICLR), 2023
Spotlight presentation
- Towards Robustness Certification Against Universal Perturbations [openreview]
Yi Zeng*, Zhouxing Shi*, Ming Jin, Feiyang Kang, Lingjuan Lyu, Cho-Jui Hsieh, Ruoxi Jia
International Conference on Learning Representations (ICLR), 2023
- Data Banzhaf: A Robust Data Valuation Framework for Machine Learning [arXiv]
Jiachen T. Wang, Ruoxi Jia
International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Oral presentation
- On Solution Functions of Optimization: Universal Approximation and Covering Number Bounds [arXiv]
Ming Jin, Vanshaj Khattar, Bilgehan Sel, Harshal Kaushik, Ruoxi Jia
Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2023
Oral presentation
- Certifiably Robust Neural ODE with Learning-based Barrier Function [link]
Runing Yang, Ruoxi Jia, Xiangyu Zhang, Ming Jin
IEEE Control Systems Letters, 2023
- ModelPred: A Framework for Predicting Trained Model from Training Data [arXiv]
Yingyan Zeng, Jiachen T. Wang, Si Chen, Hoang Anh Just, Ran Jin, Ruoxi Jia
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), 2023
- Variance Reduced Shapley Value Estimation for Trustworthy Data Valuation [arXiv]
Mengmeng Wu, Ruoxi Jia, Changle Lin, Wei Huang, Xiangyu Chang
Computers and Operations Research, 2023
- Decision-Focused Learning for Inverse Noncooperative Games: Generalization Bounds and Convergence Analysis.
Ahmad Al-Tawaha, Harshal Kaushik, Bilgehan Sel, Ruoxi Jia, Ming Jin
IFAC World Congress, 2023
- A Theoretical Analysis of Using Gradient Data for Sobolev Training in RKHS
Zain ul Abdeen, Ruoxi Jia, Vassilis Kekatos, Ming Jin
IFAC World Congress, 2023
2022
- Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning [arXiv]
Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang, Ruoxi Jia, Prateek Mittal
Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022
- CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks [arXiv]
Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, Ruoxi Jia
Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), 2022
- Just Fine-tune Twice: Selective Differential Privacy for Large Language Models [arXiv]
Weiyan Shi, Si Chen, Chiyuan Zhang, Ruoxi Jia, Zhou Yu
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022
- Selective Differential Privacy for Language Modeling [arXiv]
Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, Zhou Yu
North American Chapter of the Association for Computational Linguistics (NAACL), 2022
Oral presentation
- Label-Only Model Inversion Attacks via Boundary Repulsion [arXiv]
Mostafa Kahla, Si Chen, Hoang Anh Just, Ruoxi Jia
Conference on Computer Vision and Pattern Recognition (CVPR), 2022
- Adversarial Unlearning of Backdoors via Implicit Hypergradient [arXiv]
Yi Zeng, Si Chen, Won Park, Z. Morley Mao, Ming Jin, Ruoxi Jia
International Conference on Learning Representations (ICLR), 2022
2021
- Knowledge-Enriched Distributional Model Inversion Attacks [arXiv]
Si Chen, Moustafa Kahla, Ruoxi Jia, Guo-Jun Qi
International Conference on Computer Vision (ICCV), 2021
- Rethinking the Backdoor Attacks’ Triggers: A Frequency Perspective [arXiv]
Yi Zeng*, Won Park*, Z. Morley Mao, Ruoxi Jia
International Conference on Computer Vision (ICCV), 2021
- DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing [arXiv]
Wenxiao Wang, Tianhao Wang, Lun Wang, Nanqing Luo, Pan Zhou, Dawn Song, and Ruoxi Jia
The 21st Privacy Enhancing Technologies Symposium (PETS), 2021
- Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification? [arXiv]
Ruoxi Jia, Fan Wu, Xuehui Sun, Jiacen Xu, David Dao, Bhavya Kailkhura, Ce Zhang, Bo Li, Dawn Song
Conference on Computer Vision and Pattern Recognition (CVPR), 2021
- InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [arXiv]
Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu
International Conference on Learning Representations (ICLR), 2021
- Improving Robustness to Model Inversion Attacks via Mutual Information Regularization [arXiv]
Tianhao Wang, Yuheng Zhang, Ruoxi Jia
Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 2021
- REFIT: a Unified Watermark Removal Framework for Deep Learning Systems with Limited Data [arXiv]
Xinyun Chen, Wenxiao Wang, Chris Bender, Yiming Ding, Ruoxi Jia, Bo Li, Dawn Song
ASIACCS, 2021
- Stability-Based Analysis and Defense against Backdoor Attacks on Edge Computing Services [paper]
Yi Zhao, Ke Xu, Haiyang Wang, Bo Li, Ruoxi Jia
IEEE Network Magazine, 2021
- Adaptive Backdoor Trigger Detection in Edge-Deployed DNNs in 5G-Enabled IIoT Systems
Yi Zeng, Ruoxi Jia, Meikang Qiu
IEEE Transactions on Industrial Informatics, 2021
2020
- A Principled Approach to Data Valuation for Federated Learning [arXiv]
Tianhao Wang, Johannes Rausch, Ce Zhang, Ruoxi Jia, Dawn Song
Book Chapter in Federated Learning: Privacy and Incentive, 2020
- The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks [arXiv]
Yuheng Zhang*, Ruoxi Jia*, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Oral presentation
- Robust anomaly detection and backdoor attack detection via differential privacy [arXiv]
Min Du, Ruoxi Jia, Dawn Song
International Conference on Learning Representations (ICLR), 2020
- On the Impact of Perceptual Compression on Deep Learning [paper]
Gerald Friedland, Ruoxi Jia, Jingkang Wang, Bo Li, Nathan Mundhenk
IEEE 3rd International Conference on Multimedia Information Processing and Retrieval, 2020
Before 2020
- Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms [arXiv]
Ruoxi Jia, David Dao, Boxin Wang, Frances Ann Hubis, Nezihe Merve Gurel, Bo Li, Ce Zhang, Costas J. Spanos, Dawn Song
International Conference on Very Large Data Bases (VLDB), 2019
- Towards Efficient Data Valuation Based on the Shapley Value [arXiv]
Ruoxi Jia*, David Dao*, Boxin Wang, Frances Ann Hubis, Nick Hynes, Nezihe Merve Gurel, Bo Li, Ce Zhang, Dawn Song, Costas Spanos
International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
- Delving into Bootstrapping for Differential Privacy [paper]
Ruoxi Jia, Bo Li, Chaowei Xiao, Dawn Song
ICML Workshop on Security and Privacy of Machine Learning, 2019
- Leveraging Unlabeled Data for Watermark Removal of Deep Neural Networks [paper]
Xinyun Chen, Wenxiao Wang, Yiming Ding, Chris Bender, Ruoxi Jia, Bo Li and Dawn Song
ICML Workshop on Security and Privacy of Machine Learning, 2019
- On the Weak Neural Dependence Phenomenon in Deep Learning [paper]
Jiayao Zhang, Ruoxi Jia, Bo Li, Dawn Song.
NeurIPS Workshop on Deep Learning Theory, 2018
- Poisoning Attacks on Data-Driven Utility Learning in Games [paper]
Ruoxi Jia*, Ioannis Konstantakopoulos*, Bo Li, Costas Spanos
American Control Conference, 2018
- A Framework for Privacy-Preserving Data Publishing with Enhanced Utility for Cyber-Physical Systems [paper]
Fisayo Caleb Sangogboye*, Ruoxi Jia*, Tianzhen Hong, Costas Spanos, Mikkel Baun Kjaergaard
ACM Transactions on Sensor Networks, 2018
- Design Automation for Smart Building Systems [paper]
Ruoxi Jia*, Baihong Jin*, Ming Jin, Yuxun Zhou, Ioannis Konstantakopoulos, Han Zou, Joyce Kim, Dan Li, Weixi Gu, Reza Arghandeh, Pierluigi Nuzzo, Stefano Schiavon, Alberto L. Sangiovanni-Vincentelli, Costas Spanos.
Proceedings of the IEEE, 2018
- Advanced Building Control via Deep Reinforcement Learning [paper]
Ruoxi Jia, Ming Jin, Kaiyu Sun, Tianzhen Hong, Costas Spanos
International Conference on Applied Energy, 2018
- Buildings.Occupants: a Modelica package for modeling occupant behaviour in buildings [paper]
Zhe Wang, Tianzhen Hong, Ruoxi Jia
Journal of Building Performance Simulation, 2018
- BISCUIT: Building Intelligent System Customer Investment Tools [paper]
Ming Jin, Ruoxi Jia, Hari Prasanna Das, Wei Feng, Costas Spanos
International Conference on Applied Energy, 2018
- Virtual Occupancy Sensing: Your Energy Can Tell Whether You Are Present [paper]
Ming Jin, Ruoxi Jia, Costas Spanos
IEEE Transactions on Mobile Computing, 2017
- Data Analytics and Optimization of an Ice-Based Energy Storage System for Commercial Buildings [paper]
Na Luo, Tianzhen Hong, Hui Li, Ruoxi Jia, Wenguo Weng
Applied Energy, 2017
- Towards a Theory of Free-Lunch Privacy in Cyber-Physical Systems [paper]
Ruoxi Jia, Roy Dong, Prashanth Ganesh, Shankar Sastry, Costas Spanos
Annual Allerton Conference on Communication, Control, and Computing, 2017
- PAD: Protecting Anonymity in Publishing Building Related Datasets [paper]
Ruoxi Jia*, Fisayo Caleb Sangogboye*, Tianzhen Hong, Costas Spanos, Mikkel Baun Kjaergaard
ACM International Conference on Systems for Energy-Efficient Built Environments, 2017
- Optimal Sensor-Controller Codesign for Privacy in Dynamical Systems [paper]
Ruoxi Jia, Roy Dong, Shankar Sastry, Costas Spanos
IEEE Conference on Decision and Control, 2017
- Privacy-Enhanced Architecture for Occupancy-based HVAC Control [paper]
Ruoxi Jia, Roy Dong, Shankar Sastry, Costas Spanos
ACM/IEEE International Conference on Cyber-Physical Systems, 2017
- Occupancy Modeling in Shared Spaces of Buildings: A Queueing Approach [paper]
Ruoxi Jia, Costas Spanos
Journal of Building Performance Simulation, 2016
- MapSentinel: Can the Knowledge of Space Use Improve Indoor Tracking Further? [paper]
Ruoxi Jia, Ming Jin, Han Zou, Yigitcan Yesilata, Lihua Xie, Costas Spanos
Sensors, 2016
- A Fully Unsupervised Nonintrusive Load Monitoring Framework [paper]
Ruoxi Jia, Yang Gao, Costas Spanos
IEEE International Conference on Smart Grid Communications, 2015
- APEC: Auto Planner for Efficient Configuration of Indoor Positioning System [paper]
Ming Jin, Ruoxi Jia, Costas Spanos
International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies, 2015
- SoundLoc: Accurate Room-level Indoor Localization Using Acoustic Signatures [paper]
Ruoxi Jia, Ming Jin, Zilong Chen, Costas Spanos
IEEE International Conference on Automation Science and Engineering, 2015
- An iBeacon Assisted Indoor Localization and Tracking System [paper]
Zhenghua Chen, Qingchang Zhu, Hao Jiang, Han Zou, Yeng Chai Soh, Lihua Xie, Ruoxi Jia, Costas Spanos
International Conference on Information Processing in Sensor Networks, 2015
- Presencesense: Zero-training Algorithm for Individual Presence Detection Based on Power Monitoring [paper]
Ming Jin, Ruoxi Jia, Zhaoyi Kang, Ioannis Konstantakopoulos, Costas Spanos
ACM International Conference on Systems for Energy-Efficient Built Environments, 2014
- Environmental Sensing by Wearable Device for Indoor Activity and Location Estimation [paper]
Ming Jin, Han Zou, Kevin Weekly, Ruoxi Jia, Alexandre M Bayen, Costas Spanos
Annual Conference of the IEEE Industrial Electronics Society, 2014