This survey reviews the existing and envisioned security vulnerabilities and defense mechanisms relevant to Advanced Air Mobility (AAM) systems, with a focus on electric vertical takeoff and landing (eVTOL) aircraft. Drawing from vulnerabilities in the avionics in commercial aviation and the automated unmanned aerial systems (UAS), the paper presents a taxonomy of attacks, analyzes mitigation strategies, and proposes a secure system architecture tailored to the future AAM ecosystem. The paper also highlights key threat vectors, including Global Positioning System (GPS) jamming/spoofing, ATC radio frequency misuse, attacks on TCAS and ADS-B, possible backdoor via Electronic Flight Bag (EFB), new vulnerabilities introduced by aircraft automation and connectivity, and risks from flight management system (FMS) software, database and cloud services. Finally, this paper describes emerging defense techniques against these attacks, and open technical problems to address toward better defense mechanisms.

Autonomous Target Tracking (ATT) systems, especially ATT drones, are widely used in applications such as surveillance, border control, and law enforcement, while also being misused in stalking and destructive actions. Thus, the security of ATT is highly critical for real-world applications. Under the scope, we present a new type of attack: distance-pulling attacks (DPA) and a systematic study of it, which exploits vulnerabilities in ATT systems to dangerously reduce tracking distances, leading to drone capturing, increased susceptibility to sensor attacks, or even physical collisions. To achieve these goals, we present FlyTrap, a novel physical-world attack framework that employs an adversarial umbrella as a deployable and domain-specific attack vector. FlyTrap is specifically designed to meet key desired objectives in attacking ATT drones: physical deployability, closed-loop effectiveness, and spatial-temporal consistency. Through novel progressive distance-pulling strategy and controllable spatial-temporal consistency designs, FlyTrap manipulates ATT drones in real-world setups to achieve significant system-level impacts. Our evaluations include new datasets, metrics, and closed-loop experiments on real-world white-box and even commercial ATT drones, including DJI and HoverAir. Results demonstrate FlyTrap's ability to reduce tracking distances within the range to be captured, sensor attacked, or even directly crashed, highlighting urgent security risks and practical implications for the safe deployment of ATT systems.

Light detection and ranging (LiDAR) sensors play a crucial role in autonomous driving (AD) systems because of their high-definition 3-D sensing capabilities. While LiDAR spoofing attacks that project fake ranging signals pose a critical security threat, new-generation (new-gen) LiDARs have introduced pulse fingerprinting (PF), an authentication mechanism that distinguishes reflected signals from external interference. Although PF offers a promising defense against spoofing attacks, its security implications remain unexplored. This article presents the first comprehensive security evaluation of PF features. While current PF-equipped LiDARs use the time difference of pulse pairs as authentication to counter conventional spoofing attacks, we demonstrate their vulnerability to periodic malicious laser pulses through two novel attacks: high-frequency removal (HFR) and adaptive HFR (A-HFR). The basic HFR attack employs high-frequency laser pulses, while A-HFR incorporates weak synchronization and selective range limiting to prevent laser overheating, achieving spoofing frequencies 25x higher than HFR. Our evaluation of three commercial LiDARs with PF reveals their vulnerability to these attacks, with over 96% of the point cloud data vanishing within the attack target area. Through attack simulations against Autoware using real attack data, we show that successful attacks in over 90% of frames invariably lead to accidents, highlighting significant limitations in current PF implementations. We conclude by proposing enhanced security measures for both AD systems and PF mechanisms.

Light detection and ranging (LiDAR) sensors play a crucial role in autonomous driving (AD) systems by providing high-resolution 3-D spatial information for object detection and environmental mapping. While LiDAR spoofing attacks using malicious lasers to corrupt point clouds have been demonstrated in controlled settings, their feasibility and impact in real-world AD scenarios remain largely unexplored. We address this gap by developing a novel moving vehicle spoofing (MVS) system that enables precise long-distance tracking through infrared (IR) emission detection from LiDAR sensors, significantly enhancing the detection accuracy over previous vision-based methods. Our system integrates three key components: LiDAR detection and tracking system, the auto-aiming system, and the LiDAR spoofing system. Using the MVS system, we provide the first demonstration of LiDAR spoofing attacks posing a severe threat to real-world AD systems. Our object removal attack achieved a success rate of over 96% against a vehicle traveling at 60 km/h, maintaining its effect within the braking distance (20 m). These results confirm the real-world feasibility of such attacks and provide critical evidence of their potential impact on existing AD technologies. To counter this threat, we proposed the world's first defense method capable of detecting LiDAR spoofing attacks using raw time-of-flight (ToF) data. Our method uses fast Fourier transform (FFT) to identify attack signatures in the frequency domain, enabling real-time detection and addressing limitations of existing methods, particularly in identifying removal attacks. We achieved a detection rate exceeding 90% against high-frequency removal (HFR) attacks, which threaten even next-generation LiDAR systems. These findings demonstrate the feasibility of real-time LiDAR spoofing detection and the development of robust defenses for AD systems.

Accurate localization is essential for enabling modern full self-driving services. These services heavily rely on map-based traffic information to reduce uncertainties in recognizing lane shapes, traffic light locations, and traffic signs. Achieving this level of reliance on map information requires centimeter-level localization accuracy, which is currently only achievable with LiDAR sensors. However, LiDAR is known to be vulnerable to spoofing attacks that emit malicious lasers against LiDAR to overwrite its measurements. Once localization is compromised, the attack could lead the victim off roads or make them ignore traffic lights. Motivated by these serious safety implications, we design SLAMSpoof, the first practical LiDAR spoofing attack on localization systems for self-driving to assess the actual attack significance on autonomous vehicles. SLAMSpoof can effectively find the effective attack location based on our scan matching vulnerability score (SMVS), a point-wise metric representing the potential vulnerability to spoofing attacks. To evaluate the effectiveness of the attack, we conduct real-world experiments on ground vehicles and confirm its high capability in real-world scenarios, inducing position errors of >= 4.2 meters (more than typical lane width) for all 3 popular LiDAR-based localization algorithms. We finally discuss the potential countermeasures of this attack. Code is available at https://github.com/Keio-CSG/slamspoof

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being tailored to specific applications. However, this fine-tuning process introduces considerable safety and security vulnerabilities, especially in safety-critical cyber-physical systems. In this work, we propose the first comprehensive framework for **B**ackdoor **A**ttacks against **L**LM-based **D**ecision-making systems (BALD) in embodied AI, systematically exploring the attack surfaces and trigger mechanisms. Specifically, we propose three distinct attack mechanisms: *word injection*, *scenario manipulation*, and *knowledge injection*, targeting various components in the LLM-based decision-making pipeline. We perform extensive experiments on representative LLMs (GPT-3.5, LLaMA2, PaLM2) in autonomous driving and home robot tasks, demonstrating the effectiveness and stealthiness of our backdoor triggers across various attack channels, with cases like vehicles accelerating toward obstacles and robots placing knives on beds. Our word and knowledge injection attacks achieve nearly 100\% success rate across multiple models and datasets while requiring only limited access to the system. Our scenario manipulation attack yields success rates exceeding 65\%, reaching up to 90\%, and does not require any runtime system intrusion. We also assess the robustness of these attacks against defenses, revealing their resilience. Our findings highlight critical security vulnerabilities in embodied LLM systems and emphasize the urgent need for safeguarding these systems to mitigate potential risks.

As autonomous driving systems (ADSes) become increasingly complex and integral to daily life, the importance of understanding the nature and mitigation of software bugs in these systems has grown correspondingly. Addressing the challenges of software maintenance in autonomous driving systems (e.g., handling real-time system decisions and ensuring safety-critical reliability) is crucial due to the unique combination of real-time decision-making requirements and the high stakes of operational failures in ADSes. The potential of automated tools in this domain is promising, yet there remains a gap in our comprehension of the challenges faced and the strategies employed during manual debugging and repair of such systems. In this paper, we present an empirical study that investigates bug-fix patterns in ADSes, with the aim of improving reliability and safety. We have analyzed the commit histories and bug reports of two major autonomous driving projects, Apollo and Autoware, from 1,331 bug fixes with the study of bug symptoms, root causes, and bug-fix patterns. Our study reveals several dominant bug-fix patterns, including those related to path planning, data flow, and configuration management. Additionally, we find that the frequency distribution of bug-fix patterns varies significantly depending on their nature and types and that certain categories of bugs are recurrent and more challenging to exterminate. Based on our findings, we propose a hierarchy of ADS bugs and two taxonomies of 15 syntactic bug-fix patterns and 27 semantic bug-fix patterns that offer guidance for bug identification and resolution. We also contribute a benchmark of 1,331 ADS bug-fix instances.

Recent advancements in Vision-Language Models (VLMs) have sparked interest in their use for autonomous driving, particularly in generating interpretable driving decisions through natural language. However, the assumption that VLMs inherently provide visually grounded, reliable, and interpretable explanations for driving remains largely unexamined. To address this gap, we introduce DriveBench, a benchmark dataset designed to evaluate VLM reliability across 17 settings (clean, corrupted, and text-only inputs), encompassing 19,200 frames, 20,498 question-answer pairs, three question types, four mainstream driving tasks, and a total of 12 popular VLMs. Our findings reveal that VLMs often generate plausible responses derived from general knowledge or textual cues rather than true visual grounding, especially under degraded or missing visual inputs. This behavior, concealed by dataset imbalances and insufficient evaluation metrics, poses significant risks in safety-critical scenarios like autonomous driving. We further observe that VLMs struggle with multi-modal reasoning and display heightened sensitivity to input corruptions, leading to inconsistencies in performance. To address these challenges, we propose refined evaluation metrics that prioritize robust visual grounding and multi-modal understanding. Additionally, we highlight the potential of leveraging VLMs' awareness of corruptions to enhance their reliability, offering a roadmap for developing more trustworthy and interpretable decision-making systems in real-world autonomous driving contexts. The benchmark toolkit is publicly accessible.

The safety of autonomous cars has come under scrutiny in recent years, especially after 16 documented incidents involving Teslas (with autopilot engaged) crashing into parked emergency vehicles (police cars, ambulances, and firetrucks). While previous studies have revealed that strong light sources often introduce flare artifacts in the captured image, which degrade the image quality, the impact of flare on object detection performance remains unclear. In this research, we unveil PaniCar, a digital phenomenon that causes an object detector's confidence score to fluctuate below detection thresholds when exposed to activated emergency vehicle lighting. This vulnerability poses a significant safety risk, and can cause autonomous vehicles to fail to detect objects near emergency vehicles. In addition, this vulnerability could be exploited by adversaries to compromise the security of advanced driving assistance systems (ADASs). We assess seven commercial ADASs (Tesla Model 3, "manufacturer C", HP, Pelsee, AZDOME, Imagebon, Rexing), four object detectors (YOLO, SSD, RetinaNet, Faster R-CNN), and 14 patterns of emergency vehicle lighting to understand the influence of various technical and environmental factors. We also evaluate four SOTA flare removal methods and show that their performance and latency are insufficient for real-time driving constraints. To mitigate this risk, we propose Caracetamol, a robust framework designed to enhance the resilience of object detectors against the effects of activated emergency vehicle lighting. Our evaluation shows that on YOLOv3 and Faster RCNN, Caracetamol improves the models' average confidence of car detection by 0.20, the lower confidence bound by 0.33, and reduces the fluctuation range by 0.33. In addition, Caracetamol is capable of processing frames at a rate of between 30-50 FPS, enabling real-time ADAS car detection.

Traffic Sign Recognition (TSR) is crucial for safe and correct driving automation. Recent works revealed a general vulnerability of TSR models to physical-world adversarial attacks, which can be low-cost, highly deployable, and capable of causing severe attack effects such as hiding a critical traffic sign or spoofing a fake one. However, so far existing works generally only considered evaluating the attack effects on academic TSR models, leaving the impacts of such attacks on real-world commercial TSR systems largely unclear. In this paper, we conduct the first large-scale measurement of physical-world adversarial attacks against commercial TSR systems. Our testing results reveal that it is possible for existing attack works from academia to have highly reliable (100%) attack success against certain commercial TSR system functionality, but such attack capabilities are not generalizable, leading to much lower-than-expected attack success rates overall. We find that one potential major factor is a spatial memorization design that commonly exists in today's commercial TSR systems. We design new attack success metrics that can mathematically model the impacts of such design on the TSR system-level attack success, and use them to revisit existing attacks. Through these efforts, we uncover 7 novel observations, some of which directly challenge the observations or claims in prior works due to the introduction of the new metrics.

The rapid deployment of Autonomous Driving (AD) technologies on public roads presents significant social challenges. The security of LiDAR (Light Detection and Ranging) is one of the emerging challenges in AD deployment, given its crucial role in enabling Level 4 autonomy through accurate 3D environmental sensing. Recent lines of research have demonstrated that LiDAR can be compromised by LiDAR spoofing attacks that overwrite legitimate sensing by emitting malicious lasers to the LiDAR. However, previous studies have successfully demonstrated their attacks only in controlled environments, yet gaps exist in the feasibility of their attacks in realistic high-speed, long-distance AD scenarios. To bridge these gaps, we design a novel Moving Vehicle Spoofing (MVS) system consisting of 3 subsystems: the LiDAR detection and tracking system, the auto-aiming system, and the LiDAR spoofing system. Furthermore, we design a new object removal attack, an adaptive high-frequency removal (AHFR) attack, that can be effective even against recent LiDARs with pulse fingerprinting features, by leveraging gray-box knowledge of the scan timing of target LiDARs. With our MVS system, we are not only the first to demonstrate LiDAR spoofing attacks against practical AD scenarios where the victim vehicle is driving at high speeds (60 km/h) and the attack is launched from long distances (110 meters), but also we are the first to perform LiDAR spoofing attacks against a vehicle actually operated by a popular AD stack. Our object removal attack achieves =96% attack success rates against the vehicle driving at 60 km/h to the braking distances (20 meters). Finally, we discuss possible countermeasures against attacks with our MVS system. This study not only bridges critical gaps between LiDAR security and AD security research but also sets a foundation for developing robust countermeasures against emerging threats.

LiDAR (Light Detection And Ranging) is an indispensable sensor for precise long- and wide-range 3D sensing, which directly benefited the recent rapid deployment of autonomous driving (AD). Meanwhile, such a safety-critical application strongly motivates its security research. A recent line of research finds that one can manipulate the LiDAR point cloud and fool object detectors by firing malicious lasers against LiDAR. However, these efforts face 3 critical research gaps: (1) considering only one specific LiDAR (VLP-16); (2) assuming unvalidated attack capabilities; and (3) evaluating object detectors with limited spoofing capability modeling and setup diversity. To fill these critical research gaps, we conduct the first large-scale measurement study on LiDAR spoofing attack capabilities on object detectors with 9 popular LiDARs, covering both first- and new-generation LiDARs, and 3 major types of object detectors trained on 5 different datasets. To facilitate the measurements, we (1) identify spoofer improvements that significantly improve the latest spoofing capability, (2) identify a new object removal attack that overcomes the applicability limitation of the latest method to new-generation LiDARs, and (3) perform novel mathematical modeling for both object injection and removal attacks based on our measurement results. Through this study, we are able to uncover a total of 15 novel findings, including not only completely new ones due to the measurement angle novelty, but also many that can directly challenge the latest understandings in this problem space. We also discuss defenses.

Recent research in adversarial machine learning has focused on visual perception in Autonomous Driving (AD) and has shown that printed adversarial patches can attack object detectors. However, it is important to note that AD visual perception encompasses more than just object detection; it also includes Multiple Object Tracking (MOT). MOT enhances the robustness by compensating for object detection errors and requiring consistent object detection results across multiple frames before influencing tracking results and driving decisions. Thus, MOT makes attacks on object detection alone less effective. To attack such robust AD visual perception, a digital hijacking attack has been proposed to cause dangerous driving scenarios. However, this attack has limited effectiveness. In this paper, we introduce a novel physical-world adversarial patch attack, ControlLoc, designed to exploit hijacking vulnerabilities in entire AD visual perception. ControlLoc utilizes a two-stage process: initially identifying the optimal location for the adversarial patch, and subsequently generating the patch that can modify the perceived location and shape of objects with the optimal location. Extensive evaluations demonstrate the superior performance of ControlLoc, achieving an impressive average attack success rate of around 98.1% across various AD visual perceptions and datasets, which is four times greater effectiveness than the existing hijacking attack. The effectiveness of ControlLoc is further validated in physical-world conditions, including real vehicle tests under different conditions such as outdoor light conditions with an average attack success rate of 77.5%. AD system-level impact assessments are also included, such as vehicle collision, using industry-grade AD systems and production-grade AD simulators with an average vehicle collision rate and unnecessary emergency stop rate of 81.3%.

Denoising probabilistic diffusion models have shown breakthrough performance to generate more photo-realistic images or human-level illustrations than the prior models such as GANs. This high image-generation capability has stimulated the creation of many downstream applications in various areas. However, we find that this technology is actually a double-edged sword: we identify a new type of attack, called the Natural Denoising Diffusion (NDD) attack based on the finding that state-of-the-art deep neural network (DNN) models still hold their prediction even if we intentionally remove their robust features, which are essential to the human visual system (HVS), through text prompts. The NDD attack shows a significantly high capability to generate low-cost, model-agnostic, and transferable adversarial attacks by exploiting the natural attack capability in diffusion models. To systematically evaluate the risk of the NDD attack, we perform a large-scale empirical study with our newly created dataset, the Natural Denoising Diffusion Attack (NDDA) dataset. We evaluate the natural attack capability by answering 6 research questions. Through a user study, we find that it can achieve an 88% detection rate while being stealthy to 93% of human subjects; we also find that the non-robust features embedded by diffusion models contribute to the natural attack capability. To confirm the model-agnostic and transferable attack capability, we perform the NDD attack against the Tesla Model 3 and find that 73% of the physically printed attacks can be detected as stop signs. Our hope is that the study and dataset can help our community be aware of the risks in diffusion models and facilitate further research toward robust DNN models.

Indoor Delivery Robots (IDRs) play a vital role in the upcoming fourth industrial revolution, autonomously navigating and transporting items within indoor environments. In this work, we thus aim to conduct the first security analysis of the IDR systems considering both cyber- and physical-layer attack surface and domain-specific attack goals across security, safety, and privacy. As initial results, we formulated a general IDR system architecture from 40 commercial IDR models and then performed an initial cyber-physical attack entry point identification. We also performed an experimental analysis of a real commercial IDR robot-side software and identified several vulnerabilities. We then discuss future steps.