Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders

@article{Kim2018ZerodayMD,
  title={Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders},
  author={Jin-Young Kim and Seok-Jun Bu and Sung-Bae Cho},
  journal={Inf. Sci.},
  year={2018},
  volume={460-461},
  pages={83-102}
}
Discovering Future Malware Variants By Generating New Malware Samples Using Generative Adversarial Network
TLDR
A deep generative adversarial network is presented to generate the signature of unseen malware samples; the generated signature is potentially similar to the malware samples that may be released in the future.
Detecting Intrusive Malware with a Hybrid Generative Deep Learning Model
TLDR
This paper proposes a method called latent semantic controlling generative adversarial networks (LSC-GAN) that learns to generate malware data with i-feature from a specific Gaussian distribution which represents i- feature and distinguish it from the real.
Efficient Malware Originated Traffic Classification by Using Generative Adversarial Networks
TLDR
An approach based on deep learning referred to as TrafficGAN, which analyzes (HTTP) traffic sessions to distinguish between malware-related and normal traffic and increases the diversity of data by generating samples adversarially, which enhances the robustness of the system to detect zero-day attacks and highlights the lack of sensitive data in the security community.
DeepDetectNet vs RLAttackNet: An adversarial method to improve deep learning-based static malware detection model
TLDR
A novel method of automatic adversarial samples generation based on deep reinforcement learning that can summarize the blind spots of the original detection model and generate malware samples that can bypass DeepDetectNet.
Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning
TLDR
This paper proposes a framework for generating the adversarial malware images and retraining the classification models to improve malware detection robustness and improves the robustness of the models by means of adversarial training.
Adversarial Machine Learning Applied to Intrusion and Malware Scenarios: A Systematic Review
TLDR
A wide variety of attacks were tested and proven effective in malware and intrusion detection, although their practicality was not tested in intrusion scenarios, and it was concluded that, contrarily to malware scenarios, the variety of datasets in intrusion scenario is still very small, with the most used dataset being greatly outdated.
Using Generative Adversarial Networks for Data Augmentation in Android Malware Detection
TLDR
Experiments show that both traditional techniques and GAN can improve the accuracy of classification, but GAN could more effectively improve the classification model to detect that the dataset originally has a small number of datasets and the recognition accuracy is lower.
Black-Box Adversarial Attacks Against Deep Learning Based Malware Binaries Detection with GAN
TLDR
This work proposes a novel attack framework called GAPGAN, which generates adversarial payloads (padding bytes) with generative adversarial networks (GANs) and is the first work that performs endto-end black-box attacks at the byte-level against deep learning based malware binaries detection.
A Survey on Malware Detection with Deep Learning
TLDR
This work has overviewed current intelligent machine learning and deep learning methods to solve malware detection and presents malware feature extraction and classification methods.
Cloud Zero-Day Attack Detection Using Hidden Markov Model with Transductive Learning
TLDR
A model stated as Hidden Markov Model Transductive Deep Learning (HMM_TDL), which generates hyper alerts when an attack is implemented and exhibits a higher accuracy value of 95% than existing attack classification techniques is proposed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 46 REFERENCES
Malware Detection Using Deep Transferred Generative Adversarial Networks
TLDR
This paper proposes a transferred generative adversarial network (tGAN) for automatic classification and detection of the zero-day attack, and the proposed model gets the best performance compared with the conventional machine learning algorithms.
Adversary Resistant Deep Neural Networks with an Application to Malware Detection
TLDR
This work proposes a new adversary resistant technique that obstructs attackers from constructing impactful adversarial samples by randomly nullifying features within data vectors and theoretically validate the robustness of the technique, and empirically show that the technique significantly boosts DNN robustness to adversarialamples while maintaining high accuracy in classification.
DeepAM: a heterogeneous deep learning framework for intelligent malware detection
TLDR
Promising experimental results demonstrate that the proposed deep learning framework can further improve the overall performance in malware detection compared with traditional shallow learning methods, deep learning methods with homogeneous framework, and other existing anti-malware scanners.
Behavior analysis of malware using machine learning
  • Arshi Dhammi, M. Singh
  • Computer Science
    2015 Eighth International Conference on Contemporary Computing (IC3)
  • 2015
TLDR
This approach contributes to vital cyber situation awareness by combining different malware discovery techniques, for example, static examination, to alter the session of malware triage for cyber defense and decreases the count of false alarms.
RiskRanker: scalable and accurate zero-day android malware detection
TLDR
An automated system called RiskRanker is developed to scalably analyze whether a particular app exhibits dangerous behavior and is used to produce a prioritized list of reduced apps that merit further investigation, demonstrating the efficacy and scalability of riskRanker to police Android markets of all stripes.
Malware classification with recurrent networks
TLDR
This work proposes a different approach, which, similar to natural language modeling, learns the language of malware spoken through the executed instructions and extracts robust, time domain features.
Novel Feature Extraction, Selection and Fusion for Effective Malware Family Classification
TLDR
This paradigm is presented and discussed in the present paper, where emphasis has been given to the phases related to the extraction, and selection of a set of novel features for the effective representation of malware samples.
...
1
2
3
4
5
...