Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks

2021-06-22 · ICML Workshop AML 2021 7 · Fan Liu, Shuyu Zhao, Xuelong Dai, Bin Xiao

Meta-learning model can quickly adapt to new tasks using few-shot labeled data. However, despite achieving good generalization on few-shot classification tasks, it is still challenging to improve the adversarial robustness of the meta-learning model in few-shot learning. Although adversarial training (AT) methods such as Adversarial Query (AQ) can improve the adversarially robust performance of meta-learning models, AT is still computationally expensive training. On the other hand, meta-learning models trained with AT will drop significant accuracy on the original clean images. This paper proposed a meta-learning method on the adversarially robust neural network called Long-term Cross Adversarial Training (LCAT). LCAT will update meta-learning model parameters cross along the natural and adversarial sample distribution direction with long-term to improve both adversarial and clean few-shot classification accuracy. Due to cross-adversarial training, LCAT only needs half of the adversarial training epoch than AQ, resulting in a low adversarial training computation. Experiment results show that LCAT achieves superior performance both on the clean and adversarial few-shot classification accuracy than SOTA adversarial training methods for meta-learning models.

📄 PDF Abstract BibTeX arXiv:2106.12900

Code (1)

Gnomeek/Long-term-Cross-Adversarial-Training 공식 구현 pytorch

Tasks

Adversarial Robustness Classification Few-Shot Learning Meta-Learning

Meta Adversarial Training against Universal Patches

2021-01-27 · Jan Hendrik Metzen, Nicole Finnie, Robin Hutmacher

Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversar…

Autonomous Driving image-classification Image Classification Meta-Learning

MAD: Meta Adversarial Defense Benchmark

2023-09-18 · X. Peng, D. Zhou, G. Sun, J. Shi 외

Adversarial training (AT) is a prominent technique employed by deep learning models to defend against adversarial attacks, and to some extent, enhance model robustness. However, there are three main drawbacks of the exis…

Adversarial Defense Few-Shot Learning Meta-Learning

Meta Federated Learning

2021-02-10 · Omid Aramoon, Pin-Yu Chen, Gang Qu, Yuan Tian

Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adver…

Federated Learning Privacy Preserving

Memory-Efficient Meta-Reinforcement Learning for Adaptive Safety-Critical Control in Adversarial Spacecraft Proximity Operations

2026-06-16 · Alejandro Posadas-Nava, Richard Linares, Minduli Wijayatunga arxiv

Autonomous spacecraft rendezvous and proximity operations (RPO) require controllers that guarantee safety under thrust constraints while minimizing fuel expenditure. Input-constrained control barrier functions (ICCBFs) p…

Reinforcement Learning

Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning

2021-03-16 · ICLR 2021 1 · Namyeong Kwon, Hwidong Na, Gabriel Huang, Simon Lacoste-Julien

Model-agnostic meta-learning (MAML) is a popular method for few-shot learning but assumes that we have access to the meta-training set. In practice, training on the meta-training set may not always be an option due to da…

Few-Shot Learning Meta-Learning