|
| Ref. | Year | Description | Limitations |
|
| [10] | 2019 | Survey of approaches that detect permissions demanded by apps that might be used for malicious activities | (i) Limited to android malware detection
(ii) Permission-based malware detection only |
|
| [11] | 2017 | Deep learning techniques to detect network anomalies | (i) Only network anomaly and intrusion detection systems |
|
| [12] | 2019 | Survey of approaches to network anomaly detection | (i) Only network anomaly detection
(ii) Traditional learning based |
|
| [13] | 2018 | Different malware detection techniques, like signature- and behavior-based detection | (i) Not limited to deep learning |
|
| [14] | 2018 | A survey of intrusion detection techniques in vehicular ad hoc networks | (i) Limited to intrusion detection systems in vehicular networks |
|
| [6] | 2018 | A survey of android malware analysis using deep learning with static analysis, dynamic analysis, and hybrid analysis | (i) Limited to android malware detection
(ii) Reviewed very few publications |
|
| [15] | 2019 | A survey of machine learning techniques used in cyber security, like spam detection, phishing detection, and malware detection | (i) Traditional learning-based systems
(ii) Limited to cyber security |
|
| [7] | 2019 | Review of deep learning-based android malware detection techniques | (i) Limited to android malware detection
(ii) Reviewed very few publications |
|
| [16] | 2019 | A review of different intrusion detection systems in IoT, including anomaly based, specification based, signature based, and hybrid IDS’s | (i) IoT-based systems only
(ii) Not limited to DL- and ML-based methods |
|
| [17] | 2018 | A survey of IDS’s and defense systems in IoT | (i) IoT-based systems only
(ii) Not limited to DL and ML |
|
| [5] | 2018 | A survey of applications of deep learning techniques in malware detection | (i) Reviewed only the different DL algorithms used for malware detection |
|
| [18] | 2020 | A survey of deep learning techniques in defense against phishing | (i) Limited to phishing attacks only |
|
| [19] | 2019 | A survey of android malware detection systems | (i) Limited to Android malware
(ii) Not DL or ML based |
|
| [20] | 2019 | A survey of techniques for security in IoT | (i) Only IoT-based systems
(ii) Not limited to DL |
|
| [21] | 2019 | A survey of intrusion detection systems using deep learning | (i) Only intrusion detection systems |
|
| [8] | 2020 | A review of malware detection systems using deep learning | (i) Reviewed only about 35 publications |
|
| [22] | 2020 | An extensive review of malware detection systems based on deep learning | (i) Limited to Android malware |
|
| [9] | 2020 | A review of DL algorithms used for malware detection and some relevant literature | (i) Reviewed very few publications |
|
| Proposed study | Deep learning methods for malware and intrusion detection—a systematic literature review | Key contributions
(i) One of the extensive surveys covering a large number of research articles (94) in Windows-, Android-, and IoT-based environments for malware and intrusion detection using deep learning approaches.
(ii) Extraction of deeper malware analytics
(iii) Extraction of useful information about deep learning methods applied in the domain of malware and intrusion detection
(iv) Identification of the most effective deep learning algorithms for malware and intrusion detection
(v) Highlighting the key challenges faced during the use of deep learning methods for malware and intrusion detection |
|
