Knowledge Transfer

Securing Deep Neural Networks on Edge from Membership Inference Attacks Using Trusted Execution Environments

Yang, Cheng-Yun, Ramshankar, Gowri, Nambiar, Sudarshan, Miller, Evan, Zhang, Xun, Eliopoulos, Nicholas, Jajal, Purvish, Jing Tian, Dave, Chen, Shuo-Han, Perng, Chiy-Ferng, Lu, Yung-Hsiang

2024 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED), Newport Beach, California

Designing behavior-aware AI to improve the human-AI team performance in AI-assisted decision making

Mahmood, Syed Hasan Amin, Lu, Zhuoran, Yin, Ming

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, Jeju, Korea.

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation

Zelei Cheng, Xian Wu, Jiahao Yu, Sabrina Yang, Gang Wang, Xinyu Xing

International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024

Optimally Improving Cooperative Learning in a Social Setting

Shahrzad Haddadan, Cheng Xin, Jie Gao

International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024

Adversarial Images can Control Generative Models at Runtime

Luke Bailey, Euan Ong, Stuart Russell, Scott Emmons

International Conference on Machine Learning (ICML 2024), Vienna, Austria, July 21-27, 2024

InstructRetro: Instruction tuning post retrieval-augmented pretraining

Boxin Wang, Wei Ping, Lawrence McAfee, Peng Xu, Bo Li, Mohammad Shoeybi, Bryan Catanzaro

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Differentially private synthetic data via foundation model apis 2: Text

Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A. Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Universal consistency of wide and deep ReLU neural networks and minimax optimal convergence rates for Kolmogorov-Donoho optimal function classes

Hyunouk Ko, Xiaoming Huo

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Junyuan Hong, Jinhao Duan, Chenhui Zhang, Zhangheng Li, Chulin Xie, Kelsey Lieberman, James Diffenderfer , Brian Bartoldson , Ajay Jaiswal , Kaidi Xu , Bhavya Kailkhura , Dan Hendrycks , Dawn Song , Zhangyang Wang , Bo Li

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Harmbench: A standardized evaluation framework for automated red teaming and robust refusal

Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li , Steven Basart, Bo Li , David Forsyth , Dan Hendrycks

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models

Kang, Mintong, Nezihe Merve Gürel, Ning Yu, Dawn Song, Bo Li

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Certifiably Byzantine-Robust Federated Conformal Prediction

Mintong Kang, Zhen Lin, Jimeng Sun, Cao Xiao, Bo Li

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Grath: Gradual self-truthifying for large language models

Weixin Chen, Bo Li

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Youwei Shu, Xi Xiao, Derui Wang, Yuxin Xao, Siji Chen, Jason Xue, Linyi Li, Bo Li

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Zhaorun Chen, Zhuokai Zhao, Hongyin Luo, Huaxiu Yao, Bo Li, Jiawei Zhou

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

SHINE: Shielding Backdoors in Deep Reinforcement Learning

Wenbo Guo, Zhuowen Yuan, Jinyuan Jia, Bo Li, Dawn Song

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Yuan, Zhuowen, Zidi Xiong, Yi Zeng, Ning Yu, Ruoxi Jia, Dawn Song, and Bo Li

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

DPzero: Dimension-independent and differentially private zeroth-order optimization

Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He

International Conference on Machine Learning (ICML 2024), Vienna Austria, July 21-27, 2024
 

LLM-PBE: Assessing Data Privacy in Large Language Models

Li, Qinbin, Hong, Junyuan, Xie, Chulin, Tan, Jeffrey, Xin, Rachel, Hou, Junyi, Yin, Xavier, Wang, Zhun, Hendrycks, Dan, Wang, Zhangyang, Li, Bo, He, Bingsheng, Song, Dawn

Proceedings of the VLDB Endowment, 17(11), Pages 3201 - 3214.July 1, 2024

Poster: Brave: Byzantine-resilient and privacy-preserving peer-to-peer federated learning

Xu, Z., Jiang, F., Niu, L., Jia, J., Li, Bo, Poovendran, Radha

In Proceedings of the 19th ACM Asia Conference on Computer and Communications Security (pp. 1934-1936). Singapore

Poster: Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization

Rajabi, A., Pimple, R., Janardhanan, A., Asokraj, S., Ramasubramanian, B., Poovendran, Radha

ACM Asia Conference on Computer and Communications Security (ACM AsiaCCS), Singapore

Poster: Game of Trojans: Adaptive Adversaries Against Output-based Trojaned-Model Detectors

Sahabandu, D., Xu, X., Rajabi, A., Niu, L., Ramasubramanian, B., Bo, Li, Poovendran, Radha

ACM Asia Conference on Computer and Communications Security (ACM AsiaCCS), SingaporeJuly 1, 2024

An Inclusive Study of Petri Nets and Their Applications

McDuffie, Jasmine, Chenou, Jules

Norfolk State University College of Science, Engineering and Technology. Technical Report No.1. June 30, 2024

Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares

Gavin Brown, Jonathan Hayase, Samuel Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith

To appear in the 37th Annual Conference on Learning Theory (COLT 2024), June 30th-July 3rd, 2024 in Edmonton, Canada.

Defending Membership Inference Attack on Edge using Trusted Execution Environments

Cheng-Yun Yang, Gowri Ramshankar, Sudarshan Nambiar, Evan Miller, Xun Zhang, Nicholas Eliopoulos, Purvish Jajal, Dave Tian, Shuo-Han Chen, Chiy-Ferng Perng, Yung-Hsiang Lu

Poster at Design Automation Conference (DAC 2024), San Francisco, CA, June 23 - 27, 2024

Practical Region-level Attack against Segment Anything Models

Yifan Shen, Zhengyuan Li, Gang Wang

In Proceedings of the IEEE CVPR Workshop on Fair, Data-efficient, and Trusted Computer Vision (TCV), in conjunction with IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR), Seattle, WA, June 17-20, 2024

MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos

Jielin Qiu, Jiacheng Zhu, William Han, Aditesh Kumar, Karthik Mittal, Claire Jin, Zhengyuan Yang, Linjie Li, Jianfeng Wang, Ding Zhao, Bo Li, Lijuan Wang

Computer Vision and Pattern Recognition Conference (CVPR 2024), Seattle, WA, June 17 - 21, 2024

ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles.

Jiawei Zhang, Chejian Xu, Bo Li

Computer Vision and Pattern Recognition Conference (CVPR 2024), Seattle, WA, June 17 - 21, 2024

PerAda: Parameter-efficient and generalizable federated learning personalization with guarantees

Chulin Xie, De-An Huang, Wenda Chu, Daguang Xu, Chaowei Xiao, Bo Li, Anima Anandkumar

Computer Vision and Pattern Recognition Conference (CVPR 2024), Seattle, WA, June 17 - 21, 2024

EDC: Effective and Efficient Dialog Comprehension for Dialog State Tracking

Lu, Q., Ramasubramanian, B., Poovendran, Radha

In Proceedings of findings of 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-2024, findings), Mexico City, Mexico