Emil Lupu

Towards Poisoning Deep Learning Algorithms with Back-gradient Optimization

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.

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).[/ezcol_2third]

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.

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

Efficient Attack Graph Analysis through Approximate Inference

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 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.

Exact Inference Techniques for the Analysis of Bayesian Attack Graphs

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 (TDSC), 16(2), pp. 231-234, 2019.

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.

Paper

SECRIS: Security Risk Assessment of IoT Environments with Attack Graph Models

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.

Given the complexity of possible attacks, techniques for identifying and assessing the security risk are needed. In traditional networked environments attack graphs have been proven as a powerful tool for representing the different paths through which a system can be compromised. In this project we propose to design a new generation of attack graph models capable of describing the attack surface of modern IoT infrastructures for smart buildings. We are investigating new mechanisms to reduce the complexity of the attack graph representations and efficient algorithms for their analysis.

 

Hassan Chizari

Dr. Hassan Chizari has joined the RISS Group in February 2017, coming from Universiti Teknologi Malaysia (UTM). Hassan is a Post Doctorate Research Associate (PDRA) in Imperial College London. He did his bachelor and master degree in Shiraz University (IRAN) on ‘Computer Hardware’ and ‘Artificial Intelligence and Robotics’ respectively. He was a PhD candidate in UTM studying on Wireless Sensor Networks and he was awarded the PhD on Computer Networks. He worked in Imam Khomeini International University (IKIU) and Universiti Teknologi Malaysia (UTM) as a Lecturer and a Senior Lecturer for about 9 years. His main research interest is Wireless Sensor Network both in hardware and software perspectives and mainly in cyber-security area. Hassan has worked in the group in particular on using biophysical signals as a randomness source for establishing shared keys in wearable body sensor networks for health care. He is now an Associate Professor in Cyber-Security at the University of Gloucestershire.
Google Scholar Profile, Research Gate Profile, ORCiD Profile, Home page

Enabling Data Sharing in Contextual Environments: Policy Representation and Analysis

The paper “Enabling Data Sharing in Contextual Environments: Policy Representation and Analysis” was accepted at SACMAT 2017.

ACM Symposium on Access Control Models and Technologies (SACMAT 2017)

Authors: Erisa Karafili and Emil Lupu

Abstract: Internet of Things environments enable us to capture more and more data about the physical environment we live in and about ourselves. The data enable us to optimise resources, personalise services and offer unprecedented insights into our lives. However, to achieve these insights data need to be shared (and sometimes sold) between organisations imposing rights and obligations upon the sharing parties and in accordance with multiple layers of sometimes conflicting legislation at international, national and organisational levels. In this work, we show how such rules can be captured in a formal representation called “Data Sharing Agreements”. We introduce the use of abductive reasoning and argumentation based techniques to detect inconsistencies in the rules  applicable and resolve them by assigning priorities to the rules. We show how through the use of argumentation based techniques use-cases taken from real life application are handled flexibly addressing trade-offs between confidentiality, privacy, availability and safety.

Rabih Mohsen

Rabih has recently joined the group and contributes to several activities.

Don’ t fool me!: Detection, Characterisation and Diagnosis of Spoofed and Masked Events in Wireless Sensor Networks

dont-foolme-pic
Wireless Sensor Networks carry a high risk of being compromised, as their deployments are often unattended, physically accessible and the wireless medium is difficult to secure. Malicious data injections take place when the sensed measurements are maliciously altered to trigger wrong and potentially dangerous responses. When many sensors are compromised, they can collude with each other to alter the measurements making such changes difficult to detect. Distinguishing between genuine and malicious measurements is even more difficult when significant variations may be introduced because of events, especially if more events occur simultaneously. We propose a novel methodology based on wavelet transform to detect malicious data injections, to characterise the responsible sensors, and to distinguish malicious interference from faulty behaviours. The results, both with simulated and real measurements, show that our approach is able to counteract sophisticated attacks, achieving a significant improvement over state-of-the-art approaches.

 

Vittorio P. Illiano, Luis Muñoz-González and Emil C. Lupu: Don’ t fool me!: Detection, Characterisation and Diagnosis of Spoofed and Masked Events in Wireless Sensor Networks.

To appear in IEEE Transactions on Dependable and Secure Computing
IEEE TNSM link (open access)

Attestation in Wireless Sensor Networks: A Survey

Attestation is a mechanism used by a trusted entity to validate the software integrity of an untrusted platform. Over the past few years, several attestation techniques have been proposed. While they all use variants of a challenge-response protocol, they make different assumptions about what an attacker can and cannot do. …
Download a copy here

RISS group was part of London Duathlon!

RISS Group participated at the London Duathlon this Sunday (18/09/16) at the Duathlon Relay. Erisa Karafili ran 10km, Daniele Sgandurra cycled 44km, and Rodrigo Vieira Steiner ran 5km.

Automated Dynamic Analysis of Ransomware: Benefits, Limitations and use for Detection

Recent statistics show that in 2015 more than 140 millions new malware samples have been found. Among these, a large portion is due to ransomware, the class of malware whose specific goal is to render the victim’s system unusable, in particular 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. We present EldeRan, a machine learning approach for dynamically analysing and classifying ransomware. EldeRan monitors a set of actions performed by applications in their first phases of installation checking for characteristics signs of ransomware. Our tests over a dataset of 582 ransomware belonging to 11 families, and with 942 goodware applications, show that EldeRan achieves an area under the ROC curve of 0.995. Furthermore, EldeRan works without requiring that an entire ransomware family is available beforehand. These results suggest that dynamic analysis can support ransomware detection, since ransomware samples exhibit a set of characteristic features at run-time that are common across families, and that helps the early detection of new variants. We also outline some limitations of dynamic analysis for ransomware and propose possible solutions.

Daniele Sgandurra, Luis Muñoz-González, Rabih Mohsen, Emil C. Lupu. In ArXiv e-prints, arXiv:1609.03020, September 2016.

Formalizing Threat Models for Virtualized Systems

30th Annual IFIP WG 11.3 Working Conference on Data and Applications Security and Privacy (DBSec 2016)!

Authors: Daniele Sgandurra, Erisa Karafili and Emil Lupu.

Abstract: We propose a framework, called FATHoM (FormAlizing THreat Models), to define threat models for virtualized systems. For each component of a virtualized system, we specify a set of security proper- ties that defines its control responsibility, its vulnerability and protection states. Relations are used to represent how assumptions made about a component’s security state restrict the assumptions that can be made on the other components. FATHoM includes a set of rules to compute the derived security states from the assumptions and the components’ relations. A further set of relations and rules is used to define how to protect the derived vulnerable components. The resulting system is then analysed, among others, for consistency of the threat model. We have developed a tool that implements FATHoM, and have validated it with use-cases adapted from the literature.

Paper:Threat Model paper @ DBSec

Publisher’s Link

PETRAS Hub for the IoT

PETRAS_logo_black smallWe are thrilled to be part of the PETRAS IoT Hub which aims to ensure that the UK remains a global leader in the Internet of Things. PETRAS (Privacy, Ethics, Trust, Reliability, Acceptability and Security) groups together 9 leading UK universities and has more than 47 user partners from industry and the public sector. The consortium has received a £9.8M grant from the EPSRC. Dr Emil Lupu is to serve as Deputy Director of the Hub and lead for the Security and Safety Theme.

Evolution of Attacks, Threat Models and Solutions for Virtualized Systems

ACM DL Author-ize serviceEvolution of Attacks, Threat Models, and Solutions for Virtualized Systems

Daniele Sgandurra, Emil Lupu, ACM Computing Surveys (CSUR), Volume 48 Issue 3, Article No. 46, February 2016

Abstract: Virtualization technology enables Cloud providers to efficiently use their computing services and resources. Even if the benefits in terms of performance, maintenance, and cost are evident, however, virtualization has also been exploited by attackers to devise new ways to compromise a system. To address these problems, research security solutions have evolved considerably over the years to cope with new attacks and threat models. In this work, we review the protection strategies proposed in the literature and show how some of the solutions have been invalidated by new attacks, or threat models, that were previously not considered. The goal is to show the evolution of the threats, and of the related security and trust assumptions, in virtualized systems that have given rise to complex threat models and the corresponding sophistication of protection strategies to deal with such attacks. We also categorize threat models, security and trust assumptions, and attacks against a virtualized system at the different layers—in particular, hardware, virtualization, OS, and application.

Download citation (BibTeX format)

Exact Inference Techniques for the Dynamic Analysis of Attack Graphs

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.

Konstantina Spanaki

Konstantina joined Imperial College Business School as a Research Associate in 2014. Her main research interests focus on topics of IT adoption, business integration and information management. She worked on joint projects between this group and the Business School in particular on value aspects of data and adoption of cloud security services. Konstantina is now a Lecturer at School of Business and Economics, Loughborough University.