Artificial Intelligence has made a significant contribution to autonomous vehicles, from object detection to path planning. However, AI models require a large amount of sensitive training data and are usually computationally intensive to build. The commercial value of such models motivates attackers to mount various attacks. Adversaries can launch model extraction attacks for monetization purposes or step-ping-stone towards other attacks like model evasion. In specific cases, it even results in destroying brand reputation, differentiation, and value proposition. In addition, IP laws and AI-related legalities are still evolving and are not uniform across countries. We discuss model extraction attacks in detail with two use-cases and a generic kill-chain that can compromise autonomous cars. It is essential to investigate strategies to manage and mitigate the risk of model theft.
Sign recognition is an integral part of autonomous cars. Any misclassification of traffic signs can potentially lead to a multitude of disastrous consequences, ranging from a life-threatening accident to even a large-scale interruption of transportation services relying on autonomous cars. In this paper, we propose and examine security attacks against sign recognition systems for Deceiving Autonomous caRs with Toxic Signs (we call the proposed attacks DARTS). In particular, we introduce two novel methods to create these toxic signs. First, we propose Out-of-Distribution attacks, which expand t…
Advanced automotive active-safety systems, in general, and autonomous vehicles, in particular, rely heavily on visual data to classify and localize objects such as pedestrians, traffic signs and lights, and other nearby cars, to assist the corresponding vehicles maneuver safely in their environments. However, the performance of object detection methods could degrade rather significantly under challenging weather scenarios including rainy conditions. Despite major advancements in the development of deraining approaches, the impact of rain on object detection has largely been understudied, espec…
Deepfake technology (DT) has taken a new level of sophistication. Cybercriminals now can manipulate sounds, images, and videos to defraud and misinform individuals and businesses. This represents a growing threat to international institutions and individuals which needs to be addressed. This paper provides an overview of deepfakes, their benefits to society, and how DT works. Highlights the threats that are presented by deepfakes to businesses, politics, and judicial systems worldwide. Additionally, the paper will explore potential solutions to deepfakes and conclude with future research direc…
An Approach for Adaptive Automatic Threat Recognition Within 3D Computed Tomography Images for Baggage Security Screening
Department of Computer Science, Durham University, United Kingdom（英国杜伦大学计算机科学系）；Department of Engineering, Durham University, United Kingdom（英国杜伦大学工程系）
Mobility as a Service (MaaS) applies the everything-as-a-service paradigm of Cloud Computing to transportation: a MaaS provider offers to its users the dynamic composition of solutions of different travel agencies into a single, consistent interface. Traditionally, transits and data on mobility belong to a scattered plethora of operators. Thus, we argue that the economic model of MaaS is that of federations of providers, each trading its resources to coordinate multi-modal solutions for mobility. Such flexibility comes with many security and privacy concerns, of which insider threat is one of …
The landscape of miniaturized wireless biomedical devices (MWBDs) is rapidly expanding as proactive mobile healthcare proliferates. MWBDs are diverse and include various injectable, ingestible, implantable, and wearable devices. While the growth of MWBDs increases the flexibility of medical services, the adoption of these technologies brings privacy and security risks for their users. MWBDs can operate with sensitive, private information and affect patients through the use of stimulation and drug delivery. Therefore, these devices require trust and need to be secure. Embedding protective mecha…
With the rise of self-drive cars and connected vehicles, cars are equipped with various devices to assistant the drivers or support self-drive systems. Undoubtedly, cars have become more intelligent as we can deploy more and more devices and software on the cars. Accordingly, the security of assistant and self-drive systems in the cars becomes a life-threatening issue as smart cars can be invaded by malicious attacks that cause traffic accidents. Currently, canonical machine learning and deep learning methods are extensively employed in car hacking detection. However, machine learning and deep…
The ability to detect whether an object is a 2D or 3D object is extremely important in autonomous driving, since a detection error can have life-threatening consequences, endangering the safety of the driver, passengers, pedestrians, and others on the road. Methods proposed to distinguish between 2 and 3D objects (e.g., liveness detection methods) are not suitable for autonomous driving, because they are object dependent or do not consider the constraints associated with autonomous driving (e.g., the need for real-time decision-making while the vehicle is moving). In this paper, we present Eye…
With the proliferation of wireless networks, mobile devices and medical devices are increasingly being equipped with wireless interfaces, such as Bluetooth and WiFi to allow easy access to and control of the medical devices. Unfortunately, the very presence and usage of such interfaces also expose the medical devices to novel attacks from malicious parties. The emerging threat from malicious mobile devices is significant and severe, since attackers can steal confidential data from a patient's medical device. Also, attackers can compromise the medical device and either feed doctors bad data fro…
In this work, we examine the impact of Treadmill Assisted Gait Spoofing (TAGS) on Wearable Sensor-based Gait Authentication (WSGait). We consider more realistic implementation and deployment scenarios than the previous study, which focused only on the accelerometer sensor and a fixed set of features. Specifically, we consider the situations in which the implementation of WSGait could be using one or more sensors embedded into modern smartphones. Besides, it could be using different sets of features or different classification algorithms, or both. Despite the use of a variety of sensors, featur…
Resource Consumption Threats in Large Language Models
Beijing University of Posts and Telecommunications（北京邮电大学）；Hangzhou Dianzi University（杭州电子科技大学）；Nanyang Technological University（南洋理工大学）；Chongqing University of Posts and Telecommunications（重庆邮电大学）
We present a new machine learning and text information extraction approach to detection of cyber threat events in Twitter that are novel (previously non-extant) and developing (marked by significance with respect to similarity with a previously detected event). While some existing approaches to event detection measure novelty and trendiness, typically as independent criteria and occasionally as a holistic measure, this work focuses on detecting both novel and developing events using an unsupervised machine learning approach. Furthermore, our proposed approach enables the ranking of cyber threa…
Emerging Threats and Countermeasures in Neuromorphic Systems: A Survey
Faculty of Science and Engineering, University of Groningen（科学与工程学院，格罗宁根大学）；Faculty of Electrical Engineering and Computing, University of Zagreb（电气工程与计算学院，扎格reb大学）；Radboud University（拉德堡德大学）；Centre for Secure Information Technologies (CSIT), Queen's University Belfast（安全信息科技中心（CSIT），女王大学贝尔法斯特分校）；Faculty of Computer Science and Mathematics, University of Passau（计算机科学与数学学院，帕绍大学）；University of Amsterdam（阿姆斯特丹大学）；Digital Security (DiS) Group, Radboud University（数字安全（DiS）小组，拉德堡德大学）
Since the 2004 DARPA Grand Challenge, the autonomous driving technology has witnessed nearly two decades of rapid development. Particularly, in recent years, with the application of new sensors and deep learning technologies extending to the autonomous field, the development of autonomous driving technology has continued to make breakthroughs. Thus, many carmakers and high-tech giants dedicated to research and system development of autonomous driving. However, as the foundation of autonomous driving, the deep learning technology faces many new security risks. The academic community has propose…
Properly benchmarking a system is a difficult and intricate task. Unfortunately, even a seemingly innocuous benchmarking mistake can compromise the guarantees provided by a given systems security defense and also put its reproducibility and comparability at risk. This threat is particularly insidious as it is generally not a result of malice and can easily go undetected by both authors and reviewers. Moreover, as modern defenses often trade off security for performance in an attempt to find an ideal design point in the performance-security space, the damage caused by benchmarking mistakes is i…
Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation
School of Electrical and Computer Engineering（电气与计算机工程学院）；Georgia Institute of Technology（佐治亚理工学院）；Department of Computer Science（计算机科学系）；Rochester Institute of Technology（罗切斯特理工学院）
Chongqing University（重庆大学）；The University of Queensland（昆士兰大学）；University of Reading（雷丁大学）
To explore the robustness of recommender systems, researchers have proposed various shilling attack models and analyzed their adverse effects. Primitive attacks are highly feasible but less effective due to simplistic handcrafted rules, while upgraded attacks are more powerful but costly and difficult to deploy because they require more knowledge from recommendations. In this paper, we explore a novel shilling attack called Graph cOnvolution-based generative shilling ATtack (GOAT) to balance the attacks' feasibility and effectiveness. GOAT adopts the primitive attacks' paradigm that assigns it…
Computing and technology have vastly changed since the introduction of firewall technology in 1988. The internet has grown from a simple network of networks to a cyber and physical entity that encompasses the entire planet. Cyber-physical systems(CPS) now control most of the day to day operations of human civilization from autonomous cars to nuclear energy plants. While phenomenal, this growth spurt has created new security threats. These are threats that cannot be blocked by a firewall for they are not only cyber but cyber-physical. In light of these new cyber-physical threats, this text prop…
With the emergence of low-cost smart and connected IoT devices, the area of cyber-physical security is becoming increasingly important. Past research has demonstrated new threat vectors targeting the transition process between the cyber and physical domains, where the attacker exploits the sensing system as an attack surface for signal injection or extraction of private information. Recently, there have been attempts to characterize an abstracted model for signal injection, but they primarily focus on the path of signal processing. This paper aims to systematize the existing research on securi…
The factories of the future require efficient interconnection of their physical machines into the cyber space to cope with the emerging need of an increased uptime of machines, higher performance rates, an improved level of productivity and a collective collaboration along the supply chain. With the rapid growth of the Internet of Things (IoT), and its application in industrial areas, the so called Industrial Internet of Things (IIoT)/Industry 4.0 emerged. However, further to the rapid growth of IoT/IIoT systems, cyber attacks are an emerging threat and simple manual security testing can often…
Understanding the properties exhibited by Spatial-temporal evolution of cyber attacks improve cyber threat intelligence. In addition, better understanding on threats patterns is a key feature for cyber threats prevention, detection, and management and for enhancing defenses. In this work, we study different aspects of emerging threats in the wild shared by 160,000 global participants form all industries. First, we perform an exploratory data analysis of the collected cyber threats. We investigate the most targeted countries, most common malwares and the distribution of attacks frequency by loc…
Voltage fault injection (FI) is a well-known attack technique that can be used to force faulty behavior in processors during their operation. Glitching the supply voltage can cause data value corruption, skip security checks, or enable protected code paths. At the same time, modern systems on a chip (SoCs) are used in security-critical applications, such as self-driving cars and autonomous machines. Since these embedded devices are often physically accessible by attackers, vendors must consider device tampering in their threat models. However, while the threat of voltage FI is known since the …
As the Internet struggles to cope with scalability, mobility, and security issues, new network architectures are being proposed to better accommodate the needs of modern systems and applications. In particular, Content-Oriented Networking (CON) has emerged as a promising next-generation Internet architecture: it sets to decouple content from hosts, at the network layer, by naming data rather than hosts. CON comes with a potential for a wide range of benefits, including reduced congestion and improved delivery speed by means of content caching, simpler configuration of network devices, and secu…
