Knowledge Transfer

Multi-Modal Continual Pre-Training For Audio Encoders

Gyukah Kim, Ho-Hsiang Wu, Luca Bondi, Bing Liu

In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 691-695. IEEE, 2024.

Sok: Pitfalls in evaluating black-box attacks

Fnu Suya, Anshuman Suri, Tingwei Zhang, Jingtao Hong, Yuan Tian, David Evans

In 2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), pp. 387-407. IEEE, 2024.

Regulating advanced artificial agents

Michael K. Cohen, Noam Kolt, Yoshua Bengio, Gillian K. Hadfield, Stuart Russell

 Science 384, no. 6691 (2024): 36-38.

Does more advice help? the effects of second opinions in AI-assisted decision making

Zhuoran Lu, Dakuo Wang, Ming Yin

Proceedings of the ACM on Human-Computer Interaction 8, no. CSCW1 (2024): 1-31.

Enhancing AI-Assisted Group Decision Making through LLM-Powered Devil's Advocate

Chun-Wei Chiang, Zhuoran Lu, Zhuoyan Li, Ming Yin

In Proceedings of the 29th International Conference on Intelligent User Interfaces, pp. 103-119. 2024.

Composite Active Learning: Towards Multi-Domain Active Learning with Theoretical Guarantees

Guang-Yuan Hao, Hengguan Huang, Haotian Wang, Jie Gao, Hao Wang

In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-24), Vancouver, Canada, February 20-27, 2024

DGCluster: A Neural Framework for Attributed Graph Clustering via Modularity Maximization

Aritra Bhowmick, Mert Kosan, Zexi Huang, Ambuj Singh, Sourav Medya

In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-24), Vancouver, Canada, February 20-27, 2024

Decoding AI's Nudge: A Unified Framework to Predict Human Behavior in AI-assisted Decision Making

Zhuoyan Li, Zhuoran Lu, Ming Yin

In Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-24), Vancouver, Canada, February 20-27, 2024

Overcoming the lack of labeled data: Training malware detection models using adversarial domain adaptation

Sonam Bhardwaj, Adrian Shuai Li, Mayank Dave, Elisa Bertino

Computers & Security (2024): 103769.

Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications

Fengqing Jiang, Zhangchen Xu, Luyao Niu, Boxin Wang, Jinyuan Jia, Bo Li, Radha Poovendran

Published at NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following, December 2023.

What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

Fnu Suya, Xiao Zhang, Yuan Tian, David Evans

37th Conference on Neural Information Processing Systems (NeurIPS 2023).

Fed-Game: A Game-Theoretic Defense Against Backdoor Attacks in Federated Learning

J. Jia, Z. Yuan, D. Sahabandu, L. Niu, A. Rajabi, B. Ramasubramanian, Bo Li, Radha Poovendran

37th Conference on Neural Information Processing Systems (NeurIPS 2023)

Label poisoning is all you need

Rishi Jha, Jonathan Hayase, Sewoong Oh

37th Conference on Neural Information Processing Systems (NeurIPS 2023)

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

Xiyang Liu, Prateek Jain, Weihao Kong, Sewoong Oh, Arun Suggala

37th Conference on Neural Information Processing Systems (NeurIPS 2023)

Written testimony for the United States Senate AI Forum on Risk, Alignment, & Guarding Against Doomsday Scenarios

Stuart Russell

Written Testimony for the United States Senate AI Forum on Risk, Alignment, & Guarding Against Doomsday Scenarios

Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks

Zixuan Ke, Bing Liu, Wenhan Xiong, Asli Celikyilmaz, Haoran Li

Proceedings of The 2023 Conference on Empirical Methods in Natural Language Processing (findings, EMNLP-2023),  Singapore,  December 6 –10, 2023.

Stochastic Dynamic Information Flow Tracking game using supervised learning for detecting advanced persistent threats

Shana Moothedath, Dinuka Sahabandu, Joey Allen, Andrew Clark, Linda Bushnell, Wenke Lee, Radha Poovendran

Automatica 159 (2024): 111353.

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Zhen Xiang, Fengqing Jiang, Bhaskar Ramasubramanian, Radha Poovendran, Bo Li

Published at NeurIPS 2023 Workshop on Backdoors in Deep Learning- The Good, The Bad, and the Ugly, December 2023.

Generative AI models should include detection mechanisms as a condition for public release

Alistair Knott, Dino Pedreschi, Raja Chatila, Tapabrata Chakraborti, Susan Leavy, Ricardo Baeza-Yates, David Eyers, Andrew Trotman, Paul D. Teal, Przemyslaw Biecek, Stuart Russell, Yoshua Bengio

Ethics and Information Technology 25, no. 4 (2023): 55

Evaluating stability in massive social networks: Efficient streaming algorithms for structural balance

Vikrant Ashvinkumar, Sepehr Assadi, Chengyuan Deng, Jie Gao, Chen Wang

Proceedings of the International Conference on Randomization and Computation (RANDOM 2023),  58:1–58:23. 

Learning Prototype Classifers for Long-Tailed Recognition

Saurabh Sharma, Yongqin Xian, Ning Yu, Ambuj Singh

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23)

Learning ability of interpolating deep convolutional neural networks

Tian-Yi Zhou , Xiaoming Huo

Applied and Computational Harmonic Analysis 68 (2024): 101582.

VulChecker: Graph-based Vulnerability Localization in Source Code

Yisroel Mirsky, George Macon, Michael Brown, Carter Yagemann , Matthew Pruett, Evan Downing, Sukarno Mertoguno, Wenke Lee

In 32nd USENIX Security Symposium (USENIX Security 23), pp. 6557-6574. 2023

High-dimensional sparse index tracking based on a multi-step convex optimization approach

Fangquan Shi, Lianjie Shu, Yiling Luo, Xiaoming Huo

Quantitative Finance 23, no. 9 (2023): 1361-1372.

ARIoTEDef: Adversarially Robust IoT Early Defense System Based on Self-Evolution against Multi-step Attacks

M. Huang, H. Lee, A. Kundu, X. Chen, A. Mudgerikar, Ninghui Li, Elisa Bertino

ACM Transactions on Internet of Things

Opening statement for the hearing on Oversight of AI: Principles for Regulation

Stuart Russell

U.S. Senate Committee on the Judiciary, Subcommittee on Privacy, Technology, and the Law, Washington, D.C. 

Parameter-level soft-masking for continual learning

Tatsuya Konishi, Mori Kurokawa, Chihiro Ono, Zixuan Ke, Gyuhak Kim, Bing Liu

In International Conference on Machine Learning, pp. 17492-17505. PMLR, 2023.

Learnability and Algorithm for Continual Learning

Gyuhak Kim, Changnan Xiao, Tatsuya Konishi, Bing Liu

In International Conference on Machine Learning, pp. 16877-16896. PMLR, 2023.

Conformalization of sparse generalized linear models

Etash Guha, Eugene Ndiaye Kumar, Xiaoming Huo

In International Conference on Machine Learning, pp. 11871-11887. PMLR, 2023.

Approximation and non-parametric estimation of functions over high-dimensional spheres via deep ReLU networks

Namjoon Suh, Tian-Yi Zhou, Xiaoming Huo

 In The Eleventh International Conference on Learning Representations. 2022.