DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models B Wang*, W Chen*, H Pei*, C Xie*, M Kang*, C Zhang*, C Xu, Z Xiong, ...
NeurIPS 2023, 2023
386 2023 Mgsvf: Multi-grained slow vs. fast framework for few-shot class-incremental learning H Zhao, Y Fu, M Kang, Q Tian, F Wu, X Li
TPAMI 2021, 2021
101 * 2021 Fairness in federated learning via core-stability B Ray Chaudhury, L Li, M Kang, B Li, R Mehta
NeurIPS 2022, 2022
31 2022 DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification M Kang, D Song, B Li
NeurIPS 2023, 2023
26 2023 Label-assemble: Leveraging multiple datasets with partial labels M Kang, B Li, Z Zhu, Y Lu, EK Fishman, A Yuille, Z Zhou
ISBI 2023, 2023
17 * 2023 Certifying Some Distributional Fairness with Subpopulation Decomposition M Kang*, L Li*, M Weber, Y Liu, C Zhang, B Li
NeurIPS 2022, 2022
17 2022 C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models M Kang, NM Gürel, N Yu, D Song, B Li
ICML 2024, 2024
16 * 2024 Eia: Environmental injection attack on generalist web agents for privacy leakage Z Liao, L Mo, C Xu, M Kang, J Zhang, C Xiao, Y Tian, B Li, H Sun
arXiv preprint arXiv:2409.11295, 2024
9 2024 DecodingTrust: A comprehensive assessment of trustworthiness in GPT models. arXiv B Wang, W Chen, H Pei, C Xie, M Kang, C Zhang, C Xu, Z Xiong, R Dutta, ...
arXiv preprint arXiv:2306.11698, 2024
8 2024 COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits M Kang, NM Gürel, L Li, B Li
ICLR 2024, 2023
6 * 2023 M Kang, B Li
arXiv preprint arXiv:2407.05557, 2024
5 2024 FaShapley: Fast and Approximated Shapley Based Model Pruning Towards Certifiably Robust DNNs M Kang, L Li, B Li
SaTML 2023, 2023
4 2023 Advweb: Controllable black-box attacks on vlm-powered web agents C Xu, M Kang, J Zhang, Z Liao, L Mo, M Yuan, H Sun, B Li
arXiv preprint arXiv:2410.17401, 2024
3 2024 Certifiably Byzantine-Robust Federated Conformal Prediction M Kang, Z Lin, J Sun, C Xiao, B Li
ICML 2024, 2024
1 2024 CLAS 2024: The Competition for LLM and Agent Safety Z Xiang, Y Zeng, M Kang, C Xu, J Zhang, Z Yuan, Z Chen, C Xie, F Jiang, ...
NeurIPS 2024 Competition Track, 2024
1 2024 AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models M Kang, C Xu, B Li
arXiv preprint arXiv:2412.08608, 2024
2024 
Bo LiUniversity of Illinois at Urbana–ChampaignDirección de correo verificada de illinois.edu