Knowledge Transfer

Body transformer: Leveraging robot embodiment for policy learning

Carmelo Sferrazza, Dun-Ming Huang, Fangchen Liu, Jongmin Lee, Pieter Abbeel

In the proceedings of the Conference on Robot Learning (CoRL), Munich, Germany, November 2024

Toxicity Detection for Free

Zhanhao Hu, Julien Piet, Geng Zhao, Jiantao Jiao, David Wagner

38th Conference on Neural Information Processing Systems (NeurIPS 2024)

StruQ: Defending Against Prompt Injection with Structured Queries

Sizhe Chen, Julien Piet, Chawin Sitawarin, David Wagner

In Proceedings of the 34th USENIX Security Symposium, Seattle, WA, Aug. 13–15, 2025.August 13, 2025

SoK: Leveraging Transformers for Malware Analysis

Pradip Kunwar, Kshitiz Aryal, Maanak Gupta, Mahmoud Abdelsalam, Elisa Bertino

IEEE Transactions on Dependable and Secure Computing. 

DOI: 10.1109/TDSC.2025.3576708

Certifiably Robust RAG against Retrieval Corruption

Chong Xiang, Tong Wu, Zexuan Zhong, David Wagner, Danqi Chen, Prateek Mittal

Under review

Jasmine: Scale up JavaScript Static Security Analysis with Computation-Based Semantic Explanation

Xiao, Feng, Su, Zhongfu, Yang, Guangliang, Lee, Wenke

IEEE Symposium on Security and Privacy, San Francisco, CA 

Maximizing Truth Learning in a Social Network is NP-Hard

Uradnik, Filip, Wang, Amanda, Gao, Jie

Proceedings of the 24th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), Detroit, MI.

You Can’t Judge a Binary by Its Header: Data-Code Separation for Non-Standard ARM Binaries using Pseudo Labels

Hadjer Benkraouda, N. Diwan, Gang Wang

In 2025 IEEE Symposium on Security and Privacy (SP) (pp. 36-36). IEEE Computer Society. May, 2025.May 12, 2025

Towards Secure User Interaction in WebXR

Chandrika Mukherjee, Arjun Arunasalam, Habiba Farrukh, Reham Mohamed Aburas, Z Berkay Celik

Proceedings of the 3rd International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems

Differentially Private Range Queries with Correlated Input Perturbation

Prathamesh Dharangutte, Jie Gao, Ruobin Gong, Guanyang Wang

In Proceedings of the 28th International Conference on Artificial Intelligence and Statistics (AISTATS 2025), May 3–5, 2025.

Stronger Models are not Stronger teachers for instruction tuning

Z Xu, F Jiang, L Niu, BY Lin, R Poovendran

Proc. of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies

Dynamic gradient influencing for viral marketing using graph neural networks

Saurabh Sharma , Ambuj K. Singh

In Proc. Web Conf. (WWW), 2025, pp. 3982–3993.April 28, 2025

GraphEval36K: Benchmarking coding and reasoning capabilities of large language models on graph datasets

Q. Wu, Z. Chen, W. Corcoran, M. Sra, A. Singh

In Findings of the Association for Computational Linguistics: NAACL, Apr. 2025, pp. 8095–8117.

Vulnerability Detection with Code Language Models: How Far Are We?  

Ding, Yangruibo; Fu, Yanjun; Ibrahim, Omniyyah; Sitawarin, Chawin; Chen, Xinyun; Alomair, Basel; Wagner, David; Ray, Baishakhi; Chen, Yizheng    

In Proceedings of 47th International Conference on Software Engineering, Ottowa, Ontario, Canada.

From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis

Zhuoyan Li, Hangxiao Zhu, Zhuoran Lu, Ziang Xiao, Ming Yin

43rd ACM Conference on Human Factors in Computing Systems (CHI), Yokohama, Japan

Air-bench 2024: A safety benchmark based on regulation and policies specified risk categories

Yi Zeng, Yu Yang, Andy Zhou, Jeffrey Ziwei Tan, Yuheng Tu, Yifan Mai, Kevin Klyman, Minzhou Pan, Ruoxi Jia, Dawn Song, Percy Liang, Bo Li

13th International Conference on Learning Representations (ICLR 2025)

On the Price of Differential Privacy for Hierarchical Clustering

Chengyuan Deng, Jie Gao, Jalaj Upadhyay , Chen Wang , Samson Zhou

Postesr at the 13th International Conference on Learning Representations (ICLR 2025), Apr. 24–28, 2025.April 24, 2025

Generalizing Reasoning Problems to Longer Lengths

Changnan Xiao, Bing Liu

Proceedings of the Thirteenth International Conference on Learning Representations (ICLR-2025), Singapore

Diffusion On Syntax Trees For Program Synthesis

Shreyas Kapur, Erik Jenner, Stuart Russell

Proceedings of the Thirteenth International Conference on Learning Representations (ICLR-2025), Singapore

Mark My Words: Analyzing and Evaluating Language Model Watermarks

J. Piet, C. Sitawarin, V. Fang, N. Mu, David Wagner

In Proc. of 3rd IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), University of Copenhagen, Denmark, April 9-11, 2025.April 9, 2025

A Progressive Transformer for Unifying Binary Code Embedding and Knowledge Transfer

Lu, Hanxiao, Cai, Hongyu, Liang, Yiming, Bianchi, Antonio, Celik, Z. Berkay

Proceedings of the IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) Quebec, Canada

Approximating Metric Magnitude of Point Sets

R. Andreeva, J. Ward, P. Skraba, J. Gao, R. Sarkar

The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USAFebruary 25, 2025

ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates

Jiang, Fengqing, Xu, Zhangchen, Niu, Luyao, Lin, Bill Yuchen, Poovendran, Radha

The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USAFebruary 25, 2025

Continual Learning Using a Kernel-Based Method Over Foundation Models

Momeni, Saleh, Mazumder, Sahisnu, Liu, Bing

The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA

Will an AI with Private Information Allow Itself to be Switched Off?

Andrew Garber, Rohan Subramani, Linus Luu, Mark Bedaywi, Stuart Russell, Scott Emmons

AAAI-25 (AI Alignment track), Philadelphia, PA

A Large-Scale Measurement Study of the PROXY Protocol and its Security Implications

Stijn Pletinckx, Christopher Kruegel, Giovanni Vigna

In Proceedings of the 2025 Network and Distributed System Security (NDSS) Symposium, San Diego, CA.

Revisiting Concept Drift in Windows Malware Detection: Adaptation to Real Drifted Malware with Minimal Samples

Li, Adrian S., Iyengar, Arun, Kundu, Ashish, Bertino, Elisa

Proceedings of the 2025 Network and Distributed System Security (NDSS) Symposium, San Diego, CA.

CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling

Kaiyuan Zhang, Siyuan Cheng, Guangyu Shen, Bruno Ribeiro, Shengwei An, Pin-Yu Chen, Xiangyu Zhang, Ninghui Li

In Proceedings of the 2025 Network and Distributed System Security (NDSS) Symposium, San Diego, CA, USA, Feb. 24–28, 2025.

Continual Learning Using Only Large Language Model Prompting

Qiu, Jiabao, Zixuan Ke, Liu, Bing

The 31st International Conference on Computational Linguistics (COLING-2025), Abu Dhabi, UAE

In-Context Continual Learning Assisted by an External Continual Learner

Momeni, Saleh, Mazumder, Sahisnu, Ke, Zixuan, Liu, Bing

The 31st International Conference on Computational Linguistics (COLING-2025), Abu Dhabi, UAEJanuary 19, 2025