Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning
Cyber security is used to protect and safeguard computers and various networks from ill-intended digital threats and attacks. It is getting more difficult in the information age due to the explosion of data and technology. There is a drastic rise in the new types of attacks where the conventional si...
| Những tác giả chính: | , , , , , , |
|---|---|
| Định dạng: | Bài viết |
| Ngôn ngữ: | English |
| Được phát hành: |
MDPI AG
2021-10-01
|
| Loạt: | Algorithms |
| Những chủ đề: | |
| Truy cập trực tuyến: | https://www.mdpi.com/1999-4893/14/10/297 |
| _version_ | 1827680416186761216 |
|---|---|
| author | Shruti Patil Vijayakumar Varadarajan Devika Walimbe Siddharth Gulechha Sushant Shenoy Aditya Raina Ketan Kotecha |
| author_facet | Shruti Patil Vijayakumar Varadarajan Devika Walimbe Siddharth Gulechha Sushant Shenoy Aditya Raina Ketan Kotecha |
| author_sort | Shruti Patil |
| collection | DOAJ |
| description | Cyber security is used to protect and safeguard computers and various networks from ill-intended digital threats and attacks. It is getting more difficult in the information age due to the explosion of data and technology. There is a drastic rise in the new types of attacks where the conventional signature-based systems cannot keep up with these attacks. Machine learning seems to be a solution to solve many problems, including problems in cyber security. It is proven to be a very useful tool in the evolution of malware detection systems. However, the security of AI-based malware detection models is fragile. With advancements in machine learning, attackers have found a way to work around such detection systems using an adversarial attack technique. Such attacks are targeted at the data level, at classifier models, and during the testing phase. These attacks tend to cause the classifier to misclassify the given input, which can be very harmful in real-time AI-based malware detection. This paper proposes a framework for generating the adversarial malware images and retraining the classification models to improve malware detection robustness. Different classification models were implemented for malware detection, and attacks were established using adversarial images to analyze the model’s behavior. The robustness of the models was improved by means of adversarial training, and better attack resistance is observed. |
| first_indexed | 2024-03-10T06:47:31Z |
| format | Article |
| id | doaj.art-a4245399067c459893e1a0169add9fa4 |
| institution | Directory Open Access Journal |
| issn | 1999-4893 |
| language | English |
| last_indexed | 2024-03-10T06:47:31Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Algorithms |
| spelling | doaj.art-a4245399067c459893e1a0169add9fa42023-11-22T17:08:32ZengMDPI AGAlgorithms1999-48932021-10-01141029710.3390/a14100297Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine LearningShruti Patil0Vijayakumar Varadarajan1Devika Walimbe2Siddharth Gulechha3Sushant Shenoy4Aditya Raina5Ketan Kotecha6Symbiosis Center for Artificial Intelligence, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune 412115, IndiaSchool of Computer Science and Engineering, The University of New South Wales, Sydney 1466, AustraliaSymbiosis Center for Artificial Intelligence, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune 412115, IndiaSymbiosis Center for Artificial Intelligence, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune 412115, IndiaSymbiosis Center for Artificial Intelligence, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune 412115, IndiaSymbiosis Center for Artificial Intelligence, Symbiosis Institute of Technology, Symbiosis International (Deemed University), Pune 412115, IndiaSchool of Computer Science and Engineering, The University of New South Wales, Sydney 1466, AustraliaCyber security is used to protect and safeguard computers and various networks from ill-intended digital threats and attacks. It is getting more difficult in the information age due to the explosion of data and technology. There is a drastic rise in the new types of attacks where the conventional signature-based systems cannot keep up with these attacks. Machine learning seems to be a solution to solve many problems, including problems in cyber security. It is proven to be a very useful tool in the evolution of malware detection systems. However, the security of AI-based malware detection models is fragile. With advancements in machine learning, attackers have found a way to work around such detection systems using an adversarial attack technique. Such attacks are targeted at the data level, at classifier models, and during the testing phase. These attacks tend to cause the classifier to misclassify the given input, which can be very harmful in real-time AI-based malware detection. This paper proposes a framework for generating the adversarial malware images and retraining the classification models to improve malware detection robustness. Different classification models were implemented for malware detection, and attacks were established using adversarial images to analyze the model’s behavior. The robustness of the models was improved by means of adversarial training, and better attack resistance is observed.https://www.mdpi.com/1999-4893/14/10/297malware detectionadversarial machine learningdeep learningcyber security |
| spellingShingle | Shruti Patil Vijayakumar Varadarajan Devika Walimbe Siddharth Gulechha Sushant Shenoy Aditya Raina Ketan Kotecha Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning Algorithms malware detection adversarial machine learning deep learning cyber security |
| title | Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning |
| title_full | Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning |
| title_fullStr | Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning |
| title_full_unstemmed | Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning |
| title_short | Improving the Robustness of AI-Based Malware Detection Using Adversarial Machine Learning |
| title_sort | improving the robustness of ai based malware detection using adversarial machine learning |
| topic | malware detection adversarial machine learning deep learning cyber security |
| url | https://www.mdpi.com/1999-4893/14/10/297 |
| work_keys_str_mv | AT shrutipatil improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning AT vijayakumarvaradarajan improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning AT devikawalimbe improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning AT siddharthgulechha improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning AT sushantshenoy improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning AT adityaraina improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning AT ketankotecha improvingtherobustnessofaibasedmalwaredetectionusingadversarialmachinelearning |