STM-GAN: Sequentially Trained Multiple Generators for Mitigating Mode Collapse

Varshney, Sakshi; Srijith, P. K.; Balasubramanian, Vineeth N

doi:10.1007/978-3-030-63823-8_77

Cited by 7 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, it suffices to preserve a limited number of instances from previous flows to prevent bias (i.e., set a threshold for the maximum number of previous benign/attack samples). Furthermore, another practical approach for reproducing previous samples would be using Generative Adversarial Networks (GAN) that can support continuous updating to new data [51,52,53,54].…”

Section: Data Samplingmentioning

confidence: 99%

A Multi-Agent Adaptive Deep Learning Framework for Online Intrusion Detection

Mahdi¹,

Khajavi²,

Siavoshani³

et al. 2023

Preprint

View full text Add to dashboard Cite

The network security analyzers use intrusion detection systems (IDSes) to distinguish malicious traffic from benign ones. The deep learning-based (DL-based) IDSes are proposed to auto-extract high-level features and eliminate the time-consuming and costly signature extraction process. However, this new generation of IDSes still suffers from a number of challenges. One of the main issues of an IDS is facing traffic concept drift which manifests itself as new (i.e., zero-day) attacks, in addition to the changing behavior of benign users/applications. Furthermore, a practical DL-based IDS needs to be conformed to a distributed architecture to handle big data challenges.In this paper, we propose a framework for adapting DL-based models to the changing attack/benign traffic behaviors, considering a more practical scenario (i.e., online adaptable IDSes). This framework employs continual deep anomaly detectors in addition to the federated learning approach to solve the above-mentioned challenges. Furthermore, the proposed framework implements sequential packet labeling for each flow, which provides an attack probability score for the flow by gradually observing each flow packet and updating its estimation. We evaluate the proposed framework by employing different deep models (including CNN-based and LSTM-based) over the CIC-IDS2017 and CSE-CIC-IDS2018 datasets. Through extensive evaluations and experiments, we show that the proposed distributed framework is well adapted to the traffic concept drift. More precisely, our results indicate that the CNN-based models are well suited for continually adapting to the traffic concept drift (i.e., achieving an average detection rate of above 95% while needing just 128 new flows for the updating phase), and the LSTM-based models are a good candidate for sequential packet labeling in practical online IDSes (i.e., detecting intrusions by just observing their first 15 packets).

show abstract

Section: Data Samplingmentioning

confidence: 99%

A Multi-Agent Adaptive Deep Learning Framework for Online Intrusion Detection

Mahdi¹,

Khajavi²,

Siavoshani³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…These approaches are categorized as follows: a. Building GAN model based on multiple generators or multiple discriminators or both (Bhagyashree et al, 2020;Chavdarova & Fleuret, 2018;Mangalam & Garg, 2021;Mordido et al, 2018;Mu et al, 2022;Varshney et al, 2020;K. Zhang, 2021;Z.…”

Section: Training Instabilitymentioning

confidence: 99%

“…In parallel to the local set pair training, the global discriminator is optimized to detect samples generated by any of the local generators, and similarly, the global generator is optimized to cheat all of the local discriminators. Likely, Varshney et al (2020) proposed a GAN model using multiple generators and a single discriminator. Each generator is forced to learn a different mode through a proposed loss function.…”

Section: Gan Challengesmentioning

confidence: 99%

“…Despite the success of GAN in generative models, its training process is challenging and not a trivial task due to various issues affecting the generated samples. One of these issues is related to the quality, and the diversity of the generated samples, known as "mode collapse" (Alqahtani et al, 2019;Mordido et al, 2018;Varshney et al, 2020). In the latter issue, the generator cannot generate various samples or is strictly limited to generating identical samples without achieving progress in updating its weights during the training process, hence generating samples with a lack of diversity and lousy quality (Alqahtani et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

Mohammed

2023

WIREs Computational Stats

View full text Add to dashboard Cite

In machine learning, a generative model is responsible for generating new samples of data in terms of a probabilistic model. Generative adversarial network (GAN) has been widely used to generate realistic samples in different domains and outperforms its peers in the generative models family. However, producing a robust GAN model is not a trivial task because many challenges face the GAN during the training process and impact its performance, affecting the quality and diversity of the generated samples. In this article, we conduct a comprehensive review of GANs to present the fundamentals of GAN, including its components, types, and objective functions. Also, we present an overview of the evaluation matrices used to evaluate GAN models. Moreover, we list the applications of GANs and research work in various domains. Finally, we present the challenges that face GANs and highlight two significant issues, representing mode collapse and training instability, in addition to those research efforts that tackle these challenges.This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Deep Learning Statistical Learning and Exploratory Methods of the Data Sciences > Neural Networks

show abstract

“…In which the first neural network generates a set of samples and the second attempts to distinguish between different classes of generated and real dataset. [32][33][34][35] These generated features of a massive dataset benefit a wide range of analysis tasks such as link prediction, recommendation, and node classification. 36,37 Existing models 38,39 used a GAN model to efficiently learn the complex joint probability of all the nodes and edges from a synthesized graph.…”

Section: Limitations Of Existing Gan Modelsmentioning

confidence: 99%

GAN‐C: A generative adversarial network with a classifier for effective event prediction

Rajita

Halani

Shah

et al. 2022

Computational Intelligence

View full text Add to dashboard Cite

Event prediction is essential in social network (SN) analysis to study the SN's evolutionary patterns (communities). Machine learning (ML) models are often used to predict events in SN communities. The ML algorithms manifest the results with biasness for the same dataset. Hence, the performance of an ML model requires validation for the unseen data to avoid biasness in learning. Generally, researchers use the generative adversarial network (GAN) model for generating realistic sample data to enhance the prediction of events. It is challenging for the discriminator to learn features using a single layer with similar weights in a conventional GAN technique. Therefore, this article proposes an improved version of the GAN model named generative adversarial network classifier (GAN‐C). The proposed GAN‐C model contains an additional layer, called classifier, that generates different feature maps. Wherein weights are adjusted dynamically based on the conditions to predict the events. To be precise, conditioning the weights in a classifier layer using entropy values of the features is a simple and effective way to minimize the classifier loss function (categorical cross‐entropy). GAN‐C model results in 16% loss up to 10 batches, and after that, the loss becomes negligible and can generate non‐overlapping events. The gaps between such non‐overlapping events are analyzed using the Jensen–Shannon divergence technique. The experimental results show that the existing single‐GAN and multi‐GAN methods predict events with 79.34% and 82.17% accuracy, respectively. While the proposed GAN‐C comparatively predicts events with improved accuracy of 88.56% on the same dataset. The data generated by the GAN‐C model are also approximately 55.85% and 80.59% more realistic than multi‐GAN and single‐GAN, respectively, based on root mean square error and inception score comparisons. GAN‐C is also approximately 68.01% faster than other GAN models. Thus, this article's theoretical and experimental analysis justifies that GAN‐C works suitably for predicting events in a massive dataset.

show abstract

STM-GAN: Sequentially Trained Multiple Generators for Mitigating Mode Collapse

Cited by 7 publications

References 4 publications

A Multi-Agent Adaptive Deep Learning Framework for Online Intrusion Detection

A Multi-Agent Adaptive Deep Learning Framework for Online Intrusion Detection

A comprehensive review of generative adversarial networks: Fundamentals, applications, and challenges

GAN‐C: A generative adversarial network with a classifier for effective event prediction

Contact Info

Product

Resources

About