Andrea Paudice, Luis Muñoz-González, Andras Gyorgy, Emil C. Lupu. 2018. Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection. arXiv preprint arXiv:1802.03041.

Andrea Paudice, Luis Muñoz-González, Andras Gyorgy, Emil C. Lupu. 2018. Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection. arXiv preprint arXiv:1802.03041.

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms to extract valuable information from data and produce accurate predictions, it has been shown that these algorithms are vulnerable to attacks.

Data poisoning is one of the most relevant security threats against machine learning systems, where attackers can subvert the learning process by injecting malicious samples in the training data. Recent work in adversarial machine learning has shown that the so-called optimal attack strategies can successfully poison linear classifiers, degrading the performance of the system dramatically after compromising a small fraction of the training dataset. In this paper we propose a defence mechanism to mitigate the effect of these optimal poisoning attacks based on outlier detection. We show empirically that the adversarial examples generated by these attack strategies are quite different from genuine points, as no detectability constrains are considered to craft the attack. Hence, they can be detected with an appropriate pre-filtering of the training dataset.

Attack graphs offer a powerful framework for security risk assessment. They provide a compact representation of the attack paths that an attacker can follow to compromise network resources from the analysis of the network topology and vulnerabilities. The uncertainty about the attacker’s behaviour makes Bayesian networks suitable to model attack graphs to perform static and dynamic security risk assessment. Thus, whilst static analysis of attack graphs considers the security posture at rest, dynamic analysis accounts for evidence of compromise at run-time, helping system administrators to react against potential threats. In this paper, we introduce a Bayesian attack graph model that allows to estimate the probabilities of an attacker compromising different resources of the network. We show how exact and approximate inference techniques can be efficiently applied on Bayesian attack graph models with thousands of nodes.

Luis Muñoz-González, Emil C. Lupu, “Bayesian Attack Graphs for Security Risk Assessment.” IST-153 NATO Workshop on Cyber Resilience, 2017.

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction of the training data is controlled by the attacker and manipulated to subvert the learning process. To date, these attacks have been devised only against a limited class of binary learning algorithms, due to the inherent complexity of the gradient-based procedure used to optimize the poisoning points (a.k.a. adversarial training examples).

In this work, we first extend the definition of poisoning attacks to multi-class problems. We then propose a novel poisoning algorithm based on the idea of back-gradient optimization, i.e., to compute the gradient of interest through automatic differentiation, while also reversing the learning procedure to drastically reduce the attack complexity. Compared to current poisoning strategies, our approach is able to target a wider class of learning algorithms, trained with gradient-based procedures, including neural networks and deep learning architectures. We empirically evaluate its effectiveness on several application examples, including spam filtering, malware detection, and handwritten digit recognition. We finally show that, similarly to adversarial test examples, adversarial training examples can also be transferred across different learning algorithms.
Luis Muñoz-González, Battista Biggio, Ambra Demontis, Andrea Paudice, Vasin Wongrassamee, Emil C. Lupu, Fabio Roli. “Towards Poisoning Deep Learning Algorithms with Back-gradient Optimization.” Workshop on Artificial Intelligence and Security (AISec), 2017.

This work has been done in collaboration with the PRA Lab in the University of Cagliari, Italy.

Attack graphs provide compact representations of the attack paths an attacker can follow to compromise network resources from the analysis of network vulnerabilities and topology. These representations are a powerful tool for security risk assessment. Bayesian inference on attack graphs enables the estimation of the risk of compromise to the system’s

components given their vulnerabilities and interconnections and accounts for multi-step attacks spreading through the system. While static analysis considers the risk posture at rest, dynamic analysis also accounts for evidence of compromise, for example, from Security Information and Event Management software or forensic investigation. However, in this context, exact Bayesian inference techniques do not scale well. In this article, we show how Loopy Belief Propagation—an approximate inference technique—can be applied to attack graphs and that it scales linearly in the number of nodes for both static and dynamic analysis, making such analyses viable for larger networks. We experiment with different topologies and network clustering on synthetic Bayesian attack graphs with thousands of nodes to show that the algorithm’s accuracy is acceptable and that it converges to a stable solution. We compare sequential and parallel versions of Loopy Belief Propagation with exact inference techniques for both static and dynamic analysis, showing the advantages and gains of approximate inference techniques when scaling to larger attack graphs.
Luis Muñoz-González, Daniele Sgandurra, Andrea Paudice, Emil C. Lupu. *“Efficient Attack Graph Analysis through Approximate Inference.”* ACM Transactions on Privacy and Security, vol. 20(3), pp. 1-30, 2017.

Attack graphs are a powerful tool for security risk assessment by analysing network vulnerabilities and the paths attackers can use to compromise network resources. The uncertainty about the attacker’s behaviour makes Bayesian networks suitable to model attack graphs to perform static and dynamic analysis. Previous approaches have focused on the formalization of attack graphs into a Bayesian model rather than proposing mechanisms for their analysis. In this paper we propose to use efficient algorithms to make exact inference in Bayesian attack graphs, enabling the static and dynamic network risk assessments. To support the validity of our approach we have performed an extensive experimental evaluation on synthetic Bayesian attack graphs with different topologies, showing the computational advantages in terms of time and memory use of the proposed techniques when compared to existing approaches.

Luis Muñoz-González, Daniele Sgandurra, Martín Barrere, and Emil C. Lupu. *“Exact Inference Techniques for the Analysis of Bayesian Attack Graphs.”* IEEE Transactions on Dependable and Secure Computing (in press), 2017.

IoT environments are vulnerable: many devices can be accessed physically and are not designed with security in mind. It is often impractical to patch all the vulnerabilities or to eliminate all possible threats. Unlike more traditional computing systems IoT environments bring together the **physical**, **human** and **cyber** aspects of a system. Each can be used to compromise the other and each can contribute towards monitoring and protecting the other.

Ransomware has become one of the most prominent threats in cyber-security and recent attacks has shown the sophistication and impact of this class of malware. In essence, ransomware aims to render the victim’s system unusable by encrypting important files, and then, ask the user to pay a ransom to revert the damage. Several ransomware include sophisticated packing techniques, and are hence difficult to statically analyse. In our previous work, we developed * EldeRan*, a machine learning approach to analyse and classify ransomware dynamically. EldeRan monitors a set of actions performed by applications in their first phases of installation checking for characteristics signs of ransomware.

You can download here the dataset we collected and analysed with Cuckoo sandbox, which includes 582 samples of ransomware and 942 good applications.

Further details about the dataset can be found in the paper:

Daniele Sgandurra, Luis Muñoz-González, Rabih Mohsen, Emil C. Lupu. “*Automated Analysis of Ransomware: Benefits, Limitations, and use for Detection*.” In arXiv preprints arXiv:1609.03020, 2016.

Please, if you use our data set don’t forget to reference our work. You can copy the BIBTEX link here.

Attack graphs are a powerful tool for security risk assessment by analysing network vulnerabilities and the paths attackers can use to compromise valuable network resources. The uncertainty about the attacker’s behaviour and capabilities make Bayesian networks suitable to model attack graphs to perform static and dynamic analysis. Previous approaches have focused on the formalization of traditional attack graphs into a Bayesian model rather than proposing mechanisms for their analysis. In this paper we propose to use efficient algorithms to make exact inference in Bayesian attack graphs, enabling the static and dynamic network risk assessments. To support the validity of our proposed approach we have performed an extensive experimental evaluation on synthetic Bayesian attack graphs with different topologies, showing the computational advantages in terms of time and memory use of the proposed techniques when compared to existing approaches.

Luis Muñoz-González, Daniele Sgandurra, Martín Barrere, and Emil C. Lupu: Exact Inference Techniques for the Dynamic Analysis of Attack Graphs. arXiv preprint: arXiv:1510.02427. October, 2015.