Emil Constantin Lupu

Imperial College London | Imperial · Department of Computing

Wireless Sensor Networks carry a high risk of being compromised since 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 comp...

Wireless sensor networks (WSNs) are vulnerable and can be maliciously compromised, either physically or remotely, with potentially devastating effects. When sensor networks are used to detect the occurrence of events such as fires, intruders, or heart attacks, malicious data can be injected to create fake events, and thus trigger an undesired respo...

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 approach...

Future e-Health systems will consist of low-power on-body wireless sensors attached to mobile users that interact with an ubiquitous computing environment to monitor the health and well being of patients in hospitals or at home. Patients or health practitioners have very little technical computing expertise so these systems need to be self-configur...

The proliferation of low-power wireless communications and handheld devices has facilitated the development of pervasive systems for healthcare applications. This paper describes a body sensor network comprising a personal controller, various biosensors and actuators for pervasive healthcare. Various physiological parameters such as heart rate or b...

Neural networks are now deployed in a wide number of areas from object classification to natural language systems. Implementations using analog devices like memristors promise better power efficiency, potentially bringing these applications to a greater number of environments. However, such systems suffer from more frequent device faults and overal...

Machine learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms’ performance. Optimal attacks can be formulated as bilevel optimization problems and help to assess their robustness in worst case scenarios. We show that current approaches, which typical...

We propose a new method to quantify the impact of cyber attacks in Cyber Physical Systems (CPSs). In particular, our method allows to identify the Design Parameter (DPs) affected due to a cyber attack launched on a different set of DPs in the same CPS. To achieve this, we adopt causal graphs to causally link DPs with each other and quantify the imp...

Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal attacks can be formulated as bilevel optimization problems and help to assess their robustness in worst-case scenarios. We show that current approaches, which typical...

Cyber-Physical Systems (CPS) are exposed to a plethora of attacks and their attack surface is only increasing. However, whilst many attack paths are possible, only some can threaten the system's safety and potentially lead to loss of life. Identifying them is of essence. We propose a methodology and develop a tool-chain to systematically analyse an...

Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test time attacks in the form of Universal Adversarial Perturbations (UAPs). UAPs are a class of perturbat...

Autonomous Vehicles (AVs) are mostly reliant on LiDAR sensors which enable spatial perception of their surroundings and help make driving decisions. Recent works demonstrated attacks that aim to hide objects from AV perception, which can result in severe consequences. 3D shadows, are regions void of measurements in 3D point clouds which arise from...

Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test time attacks in the form of Universal Adversarial Perturbations (UAPs). UAPs are a class of perturbat...

We investigate the extent to which redundancy (including with diversity) can help mitigate the impact of cyber attacks that aim to reduce system performance. Using analytical techniques, we estimate impacts, in terms of monetary costs, of penalties from breaching Service Level Agreements (SLAs), and find optimal resource allocations to minimize the...

Cyber-physical systems and their smart components have a pervasive presence in all our daily activities. Unfortunately, identifying the potential threats and issues in these systems and selecting enough protection is challenging given that such environments combine human, physical and cyber aspects to the system design and implementation. Current t...

LiDAR-driven 3D sensing allows new generations of vehicles to achieve advanced levels of situation awareness. However, recent works have demonstrated that physical adversaries can spoof LiDAR return signals and deceive 3D object detectors to erroneously detect “ghost" objects. Existing defenses are either impractical or focus only on vehicles. Unfo...

Universal Adversarial Perturbations (UAPs) are input perturbations that can fool a neural network on large sets of data. They are a class of attacks that represents a significant threat as they facilitate realistic, practical, and low-cost attacks on neural networks. In this work, we derive upper bounds for the effectiveness of UAPs based on norms...

Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that regularization hyperparameters remain constant, lead to an overly pessimistic view of the algorithms' robustness and of the impact...

Universal Adversarial Perturbations (UAPs) are a prominent class of adversarial examples that exploit the systemic vulnerabilities and enable physically realizable and robust attacks against Deep Neural Networks (DNNs). UAPs generalize across many different inputs; this leads to realistic and effective attacks that can be applied at scale. In this...

Machine learning algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to degrade the algorithms' performance. We show that current approaches, which typically assume that regularization hyperparameters remain constant, lead to an overly pessimistic view of the algorithms' robustness and of the impact...

Universal Adversarial Perturbations (UAPs) are input perturbations that can fool a neural network on large sets of data. They are a class of attacks that represents a significant threat as they facilitate realistic, practical, and low-cost attacks on neural networks. In this work, we derive upper bounds for the effectiveness of UAPs based on norms...

Achieving secure communication between an Implantable Medical Device (IMD) and a gateway or programming device outside the body has showed its criticality in recent reports of vulnerabilities in cardiac devices, insulin pumps and neural implants, amongst others. The use of asymmetric cryptography is typically not a practical solution for IMDs due t...

LiDARs play a critical role in Autonomous Vehicles' (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical capabilities can be used to mount a new, even more dangerous class of attacks, namely Object Remova...

Neural network compression methods like pruning and quantization are very effective at efficiently deploying Deep Neural Networks (DNNs) on edge devices. However, DNNs remain vulnerable to adversarial examples-inconspicuous inputs that are specifically designed to fool these models. In particular, Universal Adversarial Perturbations (UAPs), are a p...

LiDAR-driven 3D sensing allows new generations of vehicles to achieve advanced levels of situation awareness. However, recent works have demonstrated that physical adversaries can spoof LiDAR return signals and deceive 3D object detectors to erroneously detect "ghost" objects. In this work, we introduce GhostBuster, a set of new techniques embodied...

Machine Learning (ML) algorithms are vulnerable to poisoning attacks, where a fraction of the training data is manipulated to deliberately degrade the algorithms' performance. Optimal poisoning attacks, which can be formulated as bilevel optimisation problems, help to assess the robustness of learning algorithms in worst-case scenarios. However, cu...

We expect an increase in the frequency and severity of cyber-attacks that comes along with the need for efficient security coun- termeasures. The process of attributing a cyber-attack helps to construct efficient and targeted mitigating and preventive security measures. In this work, we propose an argumentation-based reasoner (ABR) as a proof-of-co...

In this book chapter we describe the vulnerabilities of machine learning systems, as well as the advancements and challenges to secure them.

Convolutional Neural Networks (CNNs) used on image classification tasks such as ImageNet have been shown to be biased towards recognizing textures rather than shapes. Recent work has attempted to alleviate this by augmenting the training dataset with shape-based examples to create Stylized-ImageNet. However, in this paper we show that models traine...

Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples---perturbed inputs specifically designed to produce intentional errors in the learning algorithms at test time. Existing input-agnostic adversarial perturbations exhibit interesting visual patterns that are currently unexplained. In this paper, we introduce...

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federated Averaging, a novel algorit...

The losses arising from a system being hit by cyber attacks can be staggeringly high, but defending against such attacks can also be costly. This work proposes an attack countermeasure selection approach based on cost impact analysis that takes into account the impacts of actions by both the attacker and the defender. We consider a networked system...

We propose a novel framework to detect false data injections in a low-density sensor environment with heterogeneous sensor data. The proposed detection algorithm learns how each sensor's data correlates within the sensor network, and false data is identified by exploiting the anomalies in these correlations. When a large number of sensors measuring...

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade its performance. Optimal poisoning attacks have already been proposed to evaluate worst-case scenarios, modelling attacks as a bi-level optimisation problem. Solving these pr...

Machine learning systems are vulnerable to data poisoning, a coordinated attack where a fraction of the training dataset is manipulated by an attacker to subvert learning. In this paper we first formulate an optimal attack strategy against online learning classifiers to assess worst-case scenarios. We also propose two defence mechanisms to mitigate...

Deep Convolutional Networks (DCNs) have been shown to be sensitive to Universal Adversarial Perturbations (UAPs): input-agnostic perturbations that fool a model on large portions of a dataset. These UAPs exhibit interesting visual patterns, but this phenomena is, as yet, poorly understood. Our work shows that visually similar procedural noise patte...

We expect an increase in frequency and severity of cyber-attacks that comes along with the need of efficient security countermeasures. The process of attributing a cyber-attack helps in constructing efficient and targeted mitigative and preventive security measures. In this work, we propose an argumentation-based reasoner (ABR) that helps the analy...

The losses arising from a system being hit by cyber attacks can be staggeringly high, but defending against such attacks can also be costly. This work proposes an attack countermeasure selection approach based on cost impact analysis that takes into account the impacts of actions by both the attacker and the defender. We consider a networked system...

Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an indiscriminate way. Label flippin...

Open Datasets provide one of the most popular ways to acquire insight and information about individuals, organizations and multiple streams of knowledge. Exploring Open Datasets by applying comprehensive and rigorous techniques for data processing can provide the ground for innovation and value for everyone if the data are handled in a legal and co...

Machine learning lies at the core of many modern applications, extracting valuable information from data acquired from numerous sources. It has produced a disruptive change in society, providing new functionality, improved quality of life for users, e.g., through personalization, optimized use of resources, and the automation of many processes. How...

Software-based attestation promises to enable the integrity verification of untrusted devices without requiring any particular hardware. However, existing proposals rely on strong assumptions that hinder their deployment and might even weaken their security. One of such assumptions is that using the maximum known network round-trip time to define t...

Discovering who performed a cyber-attack or from where it originated is essential in order to determine an appropriate response and future risk mitigation measures. In this work, we propose a novel argumentation-based reasoner for analyzing and attributing cyber-attacks that combines both technical and social evidence. Our reasoner helps the digita...

Deep neural networks have been shown to be vulnerable to adversarial examples, perturbed inputs that are designed specifically to produce intentional errors in the learning algorithms. However, existing attacks are either computationally expensive or require extensive knowledge of the target model and its dataset to succeed. Hence, these methods ar...

In recent years drones have become more widely used in military and non-military applications. Automation of these drones will become more important as their use increases. Individual drones acting autonomously will be able to achieve some tasks, but swarms of autonomous drones working together will be able to achieve much more complex tasks and be...

With users being more reliant on online services for their daily activities, there is an increasing risk for them to be threatened by cyber-attacks harvesting their personal information or banking details. These attacks are often facilitated by the strong interconnectivity that exists between online accounts, in particular due to the presence of sh...

Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised by attackers both at training and test time. Machine learning systems are especially vulnerable to adversarial...

Purpose The purpose of this paper is to unfold the perceptions around additional security in cloud environments by highlighting the importance of controlling mechanisms as an approach to the ethical use of the systems. The study focuses on the effects of the controlling mechanisms in maintaining an overall secure position for the cloud and the medi...

Achieving secure communication between an Implantable Medical Device (IMD) inside the body and a gateway outside the body has showed its criticality with recent reports of hackings. The use of asymmetric cryptography is not a practical solution for IMDs due to the scarce computational and power resources, symmetric key cryptography is preferred. On...

Cybersecurity is becoming an important element in curricula at all education levels. However, the foundational knowledge on which the field of cybersecurity is being developed is fragmented, and as a result, it can be difficult for both students and educators to map coherent paths of progression through the subject. The Cyber Security Body of Knowl...

We propose a model to represent the health of WSNs that allows us to evaluate a network's ability to execute its functions. Central to this model is how we quantify the importance of each network node. As we focus on the availability of the network data, we investigate how well different centrality measures identify the significance of each node fo...

Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process, compromising the performance of the algorithm producing errors in a targeted or an indiscriminate way. Label flippin...

Luis Muñoz-González and Emil C. Lupu, from Imperial College London, explore the vulnerabilities of machine learning algorithms.

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 algori...

Measurements collected in a wireless sensor network (WSN) can be maliciously compromised through several attacks, but anomaly detection algorithms may provide resilience by detecting inconsistencies in the data. Anomaly detection can identify severe threats to WSN applications, provided that there is a sufficient amount of genuine information. This...

Data-intensive environments enable us to capture information and knowledge about the physical surroundings, to optimise our resources, enjoy personalised services and gain unprecedented insights into our lives. However, to obtain these endeavours extracted from the data, this data should be generated, collected and the insight should be exploited....

The increase of connectivity and the impact it has in every day life is raising new and existing security problems that are becoming important for social good. We introduce two particular problems: cyber attack attribution and regulatory data sharing. For both problems, decisions about which rules to apply, should be taken under incomplete and cont...

The increasing use of big data comes along with the problem of ensuring correct and secure data access. There is a need to maximise the data dissemination whilst controlling their access. Depending on the type of users different qualities and parts of data are shared. We introduce an alteration mechanism, more precisely a restriction one, based on...

In this paper, we describe an efficient methodology to guide investigators during network forensic analysis. To this end, we introduce the concept of core attack graph, a compact representation of the main routes an attacker can take towards specific network targets. Such compactness allows forensic investigators to focus their efforts on critical...

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,...

Attack graphs constitute a powerful security tool aimed at modelling the many ways in which an attacker may compromise different assets in a network. Despite their usefulness in several security-related activities (e.g. hardening, monitoring, forensics), the complexity of these graphs can massively grow as the network becomes denser and larger, thu...

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,...

Attestation and measurements inspection are different but complementary approaches towards the same goal: ascertaining the integrity of sensor nodes in wireless sensor networks. In this paper we compare the benefits and drawbacks of both techniques and seek to determine how to best combine them. However, our study shows that no single solution exis...

We examine the impact of increasing autonomy on the use of airborne drones in joint operations by collaborative parties. As the degree of automation employed increases towards the level implied by the term "autonomous", it becomes apparent that existing control mechanisms are insufficiently flexible. Using an architecture introduced by Bertino et a...

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 im...

The increase of connectivity and the impact it has in every day life is raising new and existing security problems that are becoming important for social good. We introduce two particular problems: cyber attack attribution and regulatory data sharing. For both problems, decisions about which rules to apply, should be taken under incomplete and cont...

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 fo...

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. Thus, they propose intrin...