Yet Meta Learning Can Adapt Fast, It Can Also Break Easily

Yet Meta Learning Can Adapt Fast, It Can Also Break Easily

SDM (SDM), 2020

2 September 2020

ArXiv (abs)PDF HTML

Papers citing "Yet Meta Learning Can Adapt Fast, It Can Also Break Easily"

10 / 10 papers shown

Title
Provably Robust Adaptation for Language-Empowered Foundation Models Y. Lai Xiaoyu Xue Linghui Shen Yulun Wu Gaolei Li Song Guo Kai Zhou Bin Xiao AAML 144 1 0 09 Oct 2025
Domain-Generalization to Improve Learning in Meta-Learning Algorithms Usman Anjum Chris Stockman Cat Luong J. Zhan FedML 170 0 0 13 Aug 2025
FCert: Certifiably Robust Few-Shot Classification in the Era of Foundation Models Yanting Wang Wei Zou Jinyuan Jia 221 3 0 12 Apr 2024
Are You Worthy of My Trust?: A Socioethical Perspective on the Impacts of Trustworthy AI Systems on the Environment and Human Society Jamell Dacon SILM 194 2 0 18 Sep 2023
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning Xiaoyue Duan Guoliang Kang Runqi Wang Shumin Han Shenjun Xue Tian Wang Baochang Zhang 121 2 0 28 Nov 2022
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta LearningInternational Conference on Machine Learning (ICML), 2022 Momin Abbas Quan-Wu Xiao Lisha Chen Pin-Yu Chen Tianyi Chen 425 98 0 08 Jun 2022
On sensitivity of meta-learning to support data Mayank Agarwal Mikhail Yurochkin Yuekai Sun 184 22 0 26 Oct 2021
Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples Y. Tan Penny Chong Jiamei Sun Ngai-Man Cheung Yuval Elovici Alexander Binder AAML 133 0 0 24 Oct 2021
On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-LearningInternational Conference on Learning Representations (ICLR), 2021 Ren Wang Kaidi Xu Sijia Liu Pin-Yu Chen Tsui-Wei Weng Chuang Gan Meng Wang AAML 242 53 0 20 Feb 2021
Detection of Adversarial Supports in Few-shot Classifiers Using Self-Similarity and Filtering Y. Tan Penny Chong Jiamei Sun Ngai-Man Cheung Yuval Elovici Alexander Binder 159 1 0 09 Dec 2020