Malware classification with recurrent networks

By Razvan Pascanu, Jack W. Stokes, H. Sanossian, M. Marinescu, Anil Thomas. 2015

406 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Program Analysis & Verification, Privacy & Security, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Program Analysis & Verification

In Privacy & Security

In Signal Processing

Citations in the corpus

Certified Robustness to Adversarial Examples with Differential Privacy (2018, background): “Deep neural networks (DNNs) perform exceptionally well on many artificial intelligence tasks, including safety- and security-sensitive applications such as selfdriving cars [5], malware classification [47], face recognition [46], and critical infrastructure systems [63].”
Defeating Image Obfuscation with Deep Learning (2016, methodology): “Deep neural networks have been used for malware classification in general [8, 37] and for specifically detecting Android malware [53].”
MagNet: A Two-Pronged Defense against Adversarial Examples (2017, background): “They are used in autonomous control for robots and vehicles [1, 3, 4], financial systems [32], medical treatments [31], information security [12, 29], and human-computer interaction [11, 13].”
Crafting adversarial input sequences for recurrent neural networks (2016, methodology): “Furthermore, RNNs can be used for malware classification [9].”
Learning Adversary-Resistant Deep Neural Networks (2016, unknown): “In the domain of cybersecurity, security companies have demonstrated that deep learning could offer a far better way to classify all types of malware [8, 30, 39].”
EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models (2018, background): “Static malware detection attempts to classify samples as malicious or benign without executing them, in contrast to dynamic malware detection which detects malware based on its runtime behavior including time-dependent sequences of system calls for analysis [4, 9, 18].”
Using Non-invertible Data Transformations to Build Adversary-Resistant Deep Neural Networks (2016, background): “In cybersecurity, security companies have demonstrated that deep learning could offer a far better way to detect all types of malware [27], [4], [38] and recognize such functions in binary code [32].”
Autoencoder-based feature learning for cyber security applications (2017, methodology): “The models use a wide range of structures such as Convolutional Neural Network (CNN), Auto-encoders (AEs), Recurrent Neural Networks (RNNs) and Deep Belief Networks (DBN) [13, 14, 15, 16, 17, 18, 19].”
Robust Malware Detection for Internet of (Battlefield) Things Devices Using Deep Eigenspace Learning (2019, methodology): “[20] proposed a method to model malware execution using natural language modeling.”
Using Non-invertible Data Transformations to Build Adversarial-Robust Neural Networks (2016, background): “In cybersecurity, security companies have demonstrated that deep learning could offer a far better way to detect all types of malware [27], [4], [38] and recognize such functions in binary code [32].”
Deep Android Malware Detection (2017, background): “However increasing either parameter can massively increase the computational resources needed [7], which is clearly a disadvantage of standard n-gram based malware detection approaches.”
Deep Learning for Classification of Malware System Call Sequences (2016, methodology): “[19], where they use recurrent networks for modeling system call sequences, in order to construct a “language model” for malware.”
Evaluation and Design of Robust Neural Network Defenses (2018, background): “, 2015 [105] Malware 500,000 Dynamic Yes Grosse et al.”
Malware Detection with Deep Neural Network Using Process Behavior (2016, unknown): “proposed malware detection method using RNN [7].”
On the Connection between Differential Privacy and Adversarial Robustness in Machine Learning (2018, background): “Deep neural networks (DNNs) perform exceptionally well on many artificial intelligence tasks, including safety- and security-sensitive applications such as selfdriving cars [4], malware classification [37], face recog-”
Learning Adversary-Resistant Deep Neural Networks (2016, background): “In the domain of cybersecurity, security companies have demonstrated that deep learning could offer a far better way to classify all types of malware [8], [30], [39].”
Learning to Evade Static PE Machine Learning Malware Models via Reinforcement Learning (2018, background): “Static malware detection attempts to classify samples as malicious or benign without executing them, in contrast to dynamic malware detection which detects malware based on is runtime behavior including time-dependent sequences of system calls for analysis [3, 8, 22].”
A Multimodal Deep Learning Method for Android Malware Detection Using Various Features (2019, methodology): “[25] uses the recurrent neural network to detect Windows-based malware.”
Automatically Learning Semantic Features for Defect Prediction (2016, methodology): “In addition, deep learning has also been used for malware classification [50, 69], acoustic recognition [24,36,37], etc.”