Malware Detection Using Perceptrons and Support Vector Machines

Gavriluţ, Dragoş Teodor; Cimpoeşu, Mihai; Anton, Dan; Ciortuz, Liviu

doi:10.1109/computationworld.2009.85

Cited by 27 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The layer-based attack and the attempt by an adversary to attack through a communication protocol stack is shown in Table 1. [26]. A series of methodologies were proposed to overcome this type of application layer attacks, IBM research group proposed n-grams method and this method was improved by using multiple machine learning algorithms [27].…”

Section: Discussion and Analysismentioning

confidence: 99%

A survey of IoT security threats and defenses

Ahmed¹,

Nasr²,

Abdel-Mageid³

et al. 2019

IJACR

View full text Add to dashboard Cite

The IoT points to an ever-increasing network containing the things which are not only conventional computers or mobile objects, but also the physical things similar to temperature sensors, wearable devices, watches, and other smart objects. Academics, industries, and governments are interested in studying how to connect all things in the world to the internet, called Internet of Things. Its applications contain large numbers of devices (perceptions), which are difficult to implement security methods such as encryption because of the restrictions on time, memory, processing, and energy constraints [1]. Recently, the smart devices have increased with the increased availability of distributed networks. From Figure 1. We should know that the number of devices connected to it is increasing through a positive relationship with the time. Also, the market of IoT is increasing with timeIoT is attracting for many organizations, one of them is Cisco internet business solutions group (IBSG), which reported that IoT is advantageous when the number of "objects/things" connected to the Internet is greater than the human"s connection [3]. IoT enables several applications and objects for connecting with each other through the internet to a certain scale, facilitating communication and access to information, including business as-well-as technologies related challenges to realize business benefits. These applications and objects impose a strict challenge to the security of the IoT environment and systems. For example, privacy, confidentiality, integrity, authentication, and authorization of IoT system. Moreover, the IoT environment should provide solutions for other challenges such as reliability, performance, availability, mobility, management, interoperability, scalability, and big data. IoT security is a major area of concern, it is the most impacted challenges for IoT [4].IoT architecture is divided into three layers: physical (aka perception/sensing) layer, network layer, and

show abstract

Section: Discussion and Analysismentioning

confidence: 99%

A survey of IoT security threats and defenses

Ahmed¹,

Nasr²,

Abdel-Mageid³

et al. 2019

IJACR

View full text Add to dashboard Cite

show abstract

“…This paper is an extended version of the conference papers Touili, 2018, 2016). Schultz et al (2001), Kolter and Maloof (2004), Gavrilut et al (2009), Tahan et al (2012) and Khammas et al (2015) apply machine learning techniques for malware classification. All these works use either a vector of bits (Schultz et al, 2001;Gavrilut et al, 2009) or n-grams (Kolter and Maloof, 2004;Tahan et al, 2012;Khammas et al, 2015) to represent a program.…”

Section: Representation Of Malicious Behavioursmentioning

confidence: 99%

“…Schultz et al (2001), Kolter and Maloof (2004), Gavrilut et al (2009), Tahan et al (2012) and Khammas et al (2015) apply machine learning techniques for malware classification. All these works use either a vector of bits (Schultz et al, 2001;Gavrilut et al, 2009) or n-grams (Kolter and Maloof, 2004;Tahan et al, 2012;Khammas et al, 2015) to represent a program. Such vector models allow to record some chosen information from the program, they do not represent the program's behaviours.…”

Section: Representation Of Malicious Behavioursmentioning

confidence: 99%

Extracting malicious behaviours

Touili

2022

IJICS

View full text Add to dashboard Cite

In recent years, the damage cost caused by malwares is huge. Thus, malware detection is a big challenge. The task of specifying malware takes a huge amount of time and engineering effort since it currently requires the manual study of the malicious code. Thus, in order to avoid the tedious manual analysis of malicious codes, this task has to be automatised. To this aim, we propose in this work to represent malicious behaviours using extended API call graphs, where nodes correspond to API function calls, edges specify the execution order between the API functions, and edge labels indicate the dependence relation between API functions parameters. We define new static analysis techniques that allow to extract such graphs from programs, and show how to automatically extract, from a set of malicious and benign programs, an extended API call graph that represents the malicious behaviours. Finally, we show how this graph can be used for malware detection. We implemented our techniques and obtained encouraging results: 95.66% of detection rate with 0% of false alarms.

show abstract

“…Machine learning (ML) is among the innovative technologies that have been employed towards that direction. Many works have focused on building frameworks for analysis [7], [20], [26], acquiring static features [15], [38] and classifying malware families [21], [28], [30]. A system relying on ML to detect an unknown malicious payload, without the need for removing obfuscation, was presented in [20]; text classification methods were shown to improve the detection accuracy of obfuscated samples.…”

Section: Related Workmentioning

confidence: 99%

A Novel Malware Detection System Based On Machine Learning and Binary Visualization

Baptista¹,

Shiaeles²,

Kolokotronis³

2019

Preprint

View full text Add to dashboard Cite

The continued evolution and diversity of malware constitutes a major threat in modern systems. It is well proven that security defenses currently available are ineffective to mitigate the skills and imagination of cyber-criminals necessitating the development of novel solutions. Deep learning algorithms and artificial intelligence (AI) are rapidly evolving with remarkable results in many application areas. Following the advances of AI and recognizing the need for efficient malware detection methods, this paper presents a new approach for malware detection based on binary visualization and self-organizing incremental neural networks. The proposed method's performance in detecting malicious payloads in various file types was investigated and the experimental results showed that a detection accuracy of 91.7% and 94.1% was achieved for ransomware in .pdf and .doc files respectively. With respect to other formats of malicious code and other file types, including binaries, the proposed method behaved well with an incremental detection rate that allows efficiently detecting unknown malware at real-time.

show abstract

Malware Detection Using Perceptrons and Support Vector Machines

Cited by 27 publications

References 8 publications

A survey of IoT security threats and defenses

A survey of IoT security threats and defenses

Extracting malicious behaviours

A Novel Malware Detection System Based On Machine Learning and Binary Visualization

Contact Info

Product

Resources

About