LibFewShot: A Comprehensive Library for Few-shot Learning

Li, Wenbin; Dong, Chuanqi; Tian, Pinzhuo; Qin, Tiexin; Yang, Xuesong; Wang, Ziyi; Huo, Jing; Shi, Yinghuan; Wang, Lei; Luo, Jiebo

doi:10.48550/arxiv.2109.04898

Cited by 4 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The current FSL mainly focuses on three ways (Li et al 2021): (a) Fine-tuning based methods, (b) Meta-learning based methods, and (c) Metric-learning based methods. For the fine-tuning based methods (Chen et al 2019;Liu et al 2020a;Rajasegaran et al 2020;Dhillon et al 2019;Tian et al 2020;Yang, Liu, and Xu 2021), it follows the standard transfer learning procedure (Weiss, Khoshgoftaar, and Wang 2016), which is pre-training with the base classes at first and then fine-tuning with the novel class.…”

Section: Related Workmentioning

confidence: 99%

Does Few-Shot Learning Suffer from Backdoor Attacks?

Liu,

Jia,

et al. 2024

AAAI

View full text Add to dashboard Cite

The field of few-shot learning (FSL) has shown promising results in scenarios where training data is limited, but its vulnerability to backdoor attacks remains largely unexplored. We first explore this topic by first evaluating the performance of the existing backdoor attack methods on few-shot learning scenarios. Unlike in standard supervised learning, existing backdoor attack methods failed to perform an effective attack in FSL due to two main issues. Firstly, the model tends to overfit to either benign features or trigger features, causing a tough trade-off between attack success rate and benign accuracy. Secondly, due to the small number of training samples, the dirty label or visible trigger in the support set can be easily detected by victims, which reduces the stealthiness of attacks. It seemed that FSL could survive from backdoor attacks. However, in this paper, we propose the Few-shot Learning Backdoor Attack (FLBA) to show that FSL can still be vulnerable to backdoor attacks. Specifically, we first generate a trigger to maximize the gap between poisoned and benign features. It enables the model to learn both benign and trigger features, which solves the problem of overfitting. To make it more stealthy, we hide the trigger by optimizing two types of imperceptible perturbation, namely attractive and repulsive perturbation, instead of attaching the trigger directly. Once we obtain the perturbations, we can poison all samples in the benign support set into a hidden poisoned support set and fine-tune the model on it. Our method demonstrates a high Attack Success Rate (ASR) in FSL tasks with different few-shot learning paradigms while preserving clean accuracy and maintaining stealthiness. This study reveals that few-shot learning still suffers from backdoor attacks, and its security should be given attention.

show abstract

Section: Related Workmentioning

confidence: 99%

Does Few-Shot Learning Suffer from Backdoor Attacks?

Liu,

Jia,

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…CUB200 contains 11788 images of birds in 200 species, which is widely used for fine-grained classification. Following the previous work [25], we split the categories into 130, 20, 50 for training, validation and testing.…”

Section: Datasetsmentioning

confidence: 99%

Gestalt-Guided Image Understanding for Few-Shot Learning

Song¹,

Wu²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks. However, human can quickly learn the feature of a new category from very few samples. Nevertheless, previous work has rarely considered how to mimic human cognitive behavior and apply it to few-shot learning. This paper introduces Gestalt psychology to few-shot learning and proposes Gestalt-Guided Image Understanding, a plug-and-play method called GGIU. Referring to the principle of totality and the law of closure in Gestalt psychology, we design Totality-Guided Image Understanding and Closure-Guided Image Understanding to extract image features. After that, a feature estimation module is used to estimate the accurate features of images. Extensive experiments demonstrate that our method can improve the performance of existing models effectively and flexibly without retraining or fine-tuning. Our code is released on https://github.com/skingorz/GGIU.

show abstract

“…Label smoothing is considered to be effective as a general technique to improve the performance of few-shot learning methods [27] . Therefore, label smoothing was added to the architecture.…”

Section: Mmel Architecturementioning

confidence: 99%

Visual fileless malware classification via few-shot learning

Jiang

Zhang

Shi

2023

International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2023)

View full text Add to dashboard Cite

The use of fileless technologies in malware continues to grow and fileless malware becomes more dangerous and difficult to detect. To address this challenge, we propose a novel visual method for classifying fileless malware based on few-shot learning. First, we built a fileless malware dataset, which is executed through a local virtual environment to collect malware memory dumps. Secondly, memory dumps are clipped and visualized. We developed a new memory dumps trimming method and a novel binary file visualization technique, which can remove redundant data from memory dumps, significantly compress the file size, and then represent the trimmed memory dumps as RGB images. Finally, we propose a few-shot learning framework, namely MMEL (MAML + Mean_subtraction + Euclidean_normalization + Label_Smothing), to improve the performance of the classification method. Experimental results show that our visualization technique and framework outperform other state-of-the-art few-shot learning methods.

show abstract

LibFewShot: A Comprehensive Library for Few-shot Learning

Cited by 4 publications

References 26 publications

Does Few-Shot Learning Suffer from Backdoor Attacks?

Does Few-Shot Learning Suffer from Backdoor Attacks?

Gestalt-Guided Image Understanding for Few-Shot Learning

Visual fileless malware classification via few-shot learning

Contact Info

Product

Resources

About