Qi Alfred Chen

Junjie Shen, Ningfei Wang, Ziwen Wan et al.

Autonomous Driving (AD) systems rely on AI components to make safety and correct driving decisions. Unfortunately, today's AI algorithms are known to be generally vulnerable to adversarial attacks. However, for such AI component-level vulnerabilities to be semantically impactful at the system level, it needs to address non-trivial semantic gaps both (1) from the system-level attack input spaces to those at AI component level, and (2) from AI component-level attack impacts to those at the system level. In this paper, we define such research space as semantic AI security as opposed to generic AI security. Over the past 5 years, increasingly more research works are performed to tackle such semantic AI security challenges in AD context, which has started to show an exponential growth trend. In this paper, we perform the first systematization of knowledge of such growing semantic AD AI security research space. In total, we collect and analyze 53 such papers, and systematically taxonomize them based on research aspects critical for the security field. We summarize 6 most substantial scientific gaps observed based on quantitative comparisons both vertically among existing AD AI security works and horizontally with security works from closely-related domains. With these, we are able to provide insights and potential future directions not only at the design level, but also at the research goal, methodology, and community levels. To address the most critical scientific methodology-level gap, we take the initiative to develop an open-source, uniform, and extensible system-driven evaluation platform, named PASS, for the semantic AD AI security research community. We also use our implemented platform prototype to showcase the capabilities and benefits of such a platform using representative semantic AD AI attacks.

Ruochen Jiao, Xiangguo Liu, Takami Sato et al. · berkeley

Predicting the trajectories of surrounding objects is a critical task for self-driving vehicles and many other autonomous systems. Recent works demonstrate that adversarial attacks on trajectory prediction, where small crafted perturbations are introduced to history trajectories, may significantly mislead the prediction of future trajectories and induce unsafe planning. However, few works have addressed enhancing the robustness of this important safety-critical task.In this paper, we present a novel adversarial training method for trajectory prediction. Compared with typical adversarial training on image tasks, our work is challenged by more random input with rich context and a lack of class labels. To address these challenges, we propose a method based on a semi-supervised adversarial autoencoder, which models disentangled semantic features with domain knowledge and provides additional latent labels for the adversarial training. Extensive experiments with different types of attacks demonstrate that our Semisupervised Semantics-guided Adversarial Training (SSAT) method can effectively mitigate the impact of adversarial attacks by up to 73% and outperform other popular defense methods. In addition, experiments show that our method can significantly improve the system's robust generalization to unseen patterns of attacks. We believe that such semantics-guided architecture and advancement on robust generalization is an important step for developing robust prediction models and enabling safe decision-making.

Qingzhao Zhang, Shuowei Jin, Ruiyang Zhu et al.

Collaborative perception, which greatly enhances the sensing capability of connected and autonomous vehicles (CAVs) by incorporating data from external resources, also brings forth potential security risks. CAVs' driving decisions rely on remote untrusted data, making them susceptible to attacks carried out by malicious participants in the collaborative perception system. However, security analysis and countermeasures for such threats are absent. To understand the impact of the vulnerability, we break the ground by proposing various real-time data fabrication attacks in which the attacker delivers crafted malicious data to victims in order to perturb their perception results, leading to hard brakes or increased collision risks. Our attacks demonstrate a high success rate of over 86% on high-fidelity simulated scenarios and are realizable in real-world experiments. To mitigate the vulnerability, we present a systematic anomaly detection approach that enables benign vehicles to jointly reveal malicious fabrication. It detects 91.5% of attacks with a false positive rate of 3% in simulated scenarios and significantly mitigates attack impacts in real-world scenarios.

Ningfei Wang, Yunpeng Luo, Takami Sato et al.

In autonomous driving (AD), accurate perception is indispensable to achieving safe and secure driving. Due to its safety-criticality, the security of AD perception has been widely studied. Among different attacks on AD perception, the physical adversarial object evasion attacks are especially severe. However, we find that all existing literature only evaluates their attack effect at the targeted AI component level but not at the system level, i.e., with the entire system semantics and context such as the full AD pipeline. Thereby, this raises a critical research question: can these existing researches effectively achieve system-level attack effects (e.g., traffic rule violations) in the real-world AD context? In this work, we conduct the first measurement study on whether and how effectively the existing designs can lead to system-level effects, especially for the STOP sign-evasion attacks due to their popularity and severity. Our evaluation results show that all the representative prior works cannot achieve any system-level effects. We observe two design limitations in the prior works: 1) physical model-inconsistent object size distribution in pixel sampling and 2) lack of vehicle plant model and AD system model consideration. Then, we propose SysAdv, a novel system-driven attack design in the AD context and our evaluation results show that the system-level effects can be significantly improved, i.e., the violation rate increases by around 70%.

Takami Sato, Yuki Hayakawa, Ryo Suzuki et al.

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.

Ruochen Jiao, Juyang Bai, Xiangguo Liu et al.

Predicting the future trajectories of surrounding vehicles based on their history trajectories is a critical task in autonomous driving. However, when small crafted perturbations are introduced to those history trajectories, the resulting anomalous (or adversarial) trajectories can significantly mislead the future trajectory prediction module of the ego vehicle, which may result in unsafe planning and even fatal accidents. Therefore, it is of great importance to detect such anomalous trajectories of the surrounding vehicles for system safety, but few works have addressed this issue. In this work, we propose two novel methods for learning effective and efficient representations for online anomaly detection of vehicle trajectories. Different from general time-series anomaly detection, anomalous vehicle trajectory detection deals with much richer contexts on the road and fewer observable patterns on the anomalous trajectories themselves. To address these challenges, our methods exploit contrastive learning techniques and trajectory semantics to capture the patterns underlying the driving scenarios for effective anomaly detection under supervised and unsupervised settings, respectively. We conduct extensive experiments to demonstrate that our supervised method based on contrastive learning and unsupervised method based on reconstruction with semantic latent space can significantly improve the performance of anomalous trajectory detection in their corresponding settings over various baseline methods. We also demonstrate our methods' generalization ability to detect unseen patterns of anomalies.

Ningfei Wang, Shaoyuan Xie, Takami Sato et al.

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.

Takami Sato, Justin Yue, Nanze Chen et al.

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.

Junchi Lu, Xinke Li, Yuheng Liu et al.

The increasing use of generative models such as diffusion models for synthetic data augmentation has greatly reduced the cost of data collection and labeling in downstream perception tasks. However, this new data source paradigm may introduce important security concerns. Publicly available generative models are often reused without verification, raising a fundamental question of their safety and trustworthiness. This work investigates backdoor propagation in such emerging generative data supply chain, namely, Data-Chain Backdoor (DCB). Specifically, we find that open-source diffusion models can become hidden carriers of backdoors. Their strong distribution-fitting ability causes them to memorize and reproduce backdoor triggers in generation, which are subsequently inherited by downstream models, resulting in severe security risks. This threat is particularly concerning under clean-label attack scenarios, as it remains effective while having negligible impact on the utility of the synthetic data. We study two attacker choices to obtain a backdoor-carried generator, training from scratch and fine-tuning. While naive fine-tuning leads to weak inheritance of the backdoor, we find that novel designs in the loss objectives and trigger processing can substantially improve the generator's ability to preserve trigger patterns, making fine-tuning a low-cost attack path. We evaluate the effectiveness of DCB under the standard augmentation protocol and further assess data-scarce settings. Across multiple trigger types, we observe that the trigger pattern can be consistently retained in the synthetic data with attack efficacy comparable to the conventional backdoor attack.

Go Tsuruoka, Takami Sato, Qi Alfred Chen et al.

Traffic sign recognition plays a critical role in ensuring safe and efficient transportation of autonomous vehicles but remain vulnerable to adversarial attacks using stickers or laser projections. While existing attack vectors demonstrate security concerns, they suffer from visual detectability or implementation constraints, suggesting unexplored vulnerability surfaces in TSR systems. We introduce the Adversarial Retroreflective Patch (ARP), a novel attack vector that combines the high deployability of patch attacks with the stealthiness of laser projections by utilizing retroreflective materials activated only under victim headlight illumination. We develop a retroreflection simulation method and employ black-box optimization to maximize attack effectiveness. ARP achieves $\geq$93.4\% success rate in dynamic scenarios at 35 meters and $\geq$60\% success rate against commercial TSR systems in real-world conditions. Our user study demonstrates that ARP attacks maintain near-identical stealthiness to benign signs while achieving $\geq$1.9\% higher stealthiness scores than previous patch attacks. We propose the DPR Shield defense, employing strategically placed polarized filters, which achieves $\geq$75\% defense success rates for stop signs and speed limit signs against micro-prism patches.

Qingzhao Zhang, Shengtuo Hu, Jiachen Sun et al.

Trajectory prediction is a critical component for autonomous vehicles (AVs) to perform safe planning and navigation. However, few studies have analyzed the adversarial robustness of trajectory prediction or investigated whether the worst-case prediction can still lead to safe planning. To bridge this gap, we study the adversarial robustness of trajectory prediction models by proposing a new adversarial attack that perturbs normal vehicle trajectories to maximize the prediction error. Our experiments on three models and three datasets show that the adversarial prediction increases the prediction error by more than 150%. Our case studies show that if an adversary drives a vehicle close to the target AV following the adversarial trajectory, the AV may make an inaccurate prediction and even make unsafe driving decisions. We also explore possible mitigation techniques via data augmentation and trajectory smoothing. The implementation is open source at https://github.com/zqzqz/AdvTrajectoryPrediction.

Ziwen Wan, Junjie Shen, Jalen Chuang et al.

In high-level Autonomous Driving (AD) systems, behavioral planning is in charge of making high-level driving decisions such as cruising and stopping, and thus highly securitycritical. In this work, we perform the first systematic study of semantic security vulnerabilities specific to overly-conservative AD behavioral planning behaviors, i.e., those that can cause failed or significantly-degraded mission performance, which can be critical for AD services such as robo-taxi/delivery. We call them semantic Denial-of-Service (DoS) vulnerabilities, which we envision to be most generally exposed in practical AD systems due to the tendency for conservativeness to avoid safety incidents. To achieve high practicality and realism, we assume that the attacker can only introduce seemingly-benign external physical objects to the driving environment, e.g., off-road dumped cardboard boxes. To systematically discover such vulnerabilities, we design PlanFuzz, a novel dynamic testing approach that addresses various problem-specific design challenges. Specifically, we propose and identify planning invariants as novel testing oracles, and design new input generation to systematically enforce problemspecific constraints for attacker-introduced physical objects. We also design a novel behavioral planning vulnerability distance metric to effectively guide the discovery. We evaluate PlanFuzz on 3 planning implementations from practical open-source AD systems, and find that it can effectively discover 9 previouslyunknown semantic DoS vulnerabilities without false positives. We find all our new designs necessary, as without each design, statistically significant performance drops are generally observed. We further perform exploitation case studies using simulation and real-vehicle traces. We discuss root causes and potential fixes.

Won Park, Nan Liu, Qi Alfred Chen et al.

A critical aspect of autonomous vehicles (AVs) is the object detection stage, which is increasingly being performed with sensor fusion models: multimodal 3D object detection models which utilize both 2D RGB image data and 3D data from a LIDAR sensor as inputs. In this work, we perform the first study to analyze the robustness of a high-performance, open source sensor fusion model architecture towards adversarial attacks and challenge the popular belief that the use of additional sensors automatically mitigate the risk of adversarial attacks. We find that despite the use of a LIDAR sensor, the model is vulnerable to our purposefully crafted image-based adversarial attacks including disappearance, universal patch, and spoofing. After identifying the underlying reason, we explore some potential defenses and provide some recommendations for improved sensor fusion models.

Yulong Cao*, Ningfei Wang*, Chaowei Xiao* et al.

In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite various prior studies on its security issues, all of them only consider attacks on camera- or LiDAR-based AD perception alone. However, production AD systems today predominantly adopt a Multi-Sensor Fusion (MSF) based design, which in principle can be more robust against these attacks under the assumption that not all fusion sources are (or can be) attacked at the same time. In this paper, we present the first study of security issues of MSF-based perception in AD systems. We directly challenge the basic MSF design assumption above by exploring the possibility of attacking all fusion sources simultaneously. This allows us for the first time to understand how much security guarantee MSF can fundamentally provide as a general defense strategy for AD perception. We formulate the attack as an optimization problem to generate a physically-realizable, adversarial 3D-printed object that misleads an AD system to fail in detecting it and thus crash into it. We propose a novel attack pipeline that addresses two main design challenges: (1) non-differentiable target camera and LiDAR sensing systems, and (2) non-differentiable cell-level aggregated features popularly used in LiDAR-based AD perception. We evaluate our attack on MSF included in representative open-source industry-grade AD systems in real-world driving scenarios. Our results show that the attack achieves over 90% success rate across different object types and MSF. Our attack is also found stealthy, robust to victim positions, transferable across MSF algorithms, and physical-world realizable after being 3D-printed and captured by LiDAR and camera devices. To concretely assess the end-to-end safety impact, we further perform simulation evaluation and show that it can cause a 100% vehicle collision rate for an industry-grade AD system.

Shaoyuan Xie, Lingdong Kong, Yuhao Dong et al.

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.

Chen Ma, Ningfei Wang, Qi Alfred Chen et al.

In Autonomous Driving (AD), real-time perception is a critical component responsible for detecting surrounding objects to ensure safe driving. While researchers have extensively explored the integrity of AD perception due to its safety and security implications, the aspect of availability (real-time performance) or latency has received limited attention. Existing works on latency-based attack have focused mainly on object detection, i.e., a component in camera-based AD perception, overlooking the entire camera-based AD perception, which hinders them to achieve effective system-level effects, such as vehicle crashes. In this paper, we propose SlowTrack, a novel framework for generating adversarial attacks to increase the execution time of camera-based AD perception. We propose a novel two-stage attack strategy along with the three new loss function designs. Our evaluation is conducted on four popular camera-based AD perception pipelines, and the results demonstrate that SlowTrack significantly outperforms existing latency-based attacks while maintaining comparable imperceptibility levels. Furthermore, we perform the evaluation on Baidu Apollo, an industry-grade full-stack AD system, and LGSVL, a production-grade AD simulator, with two scenarios to compare the system-level effects of SlowTrack and existing attacks. Our evaluation results show that the system-level effects can be significantly improved, i.e., the vehicle crash rate of SlowTrack is around 95% on average while existing works only have around 30%.

Takami Sato, Sri Hrushikesh Varma Bhupathiraju, Michael Clifford et al.

All vehicles must follow the rules that govern traffic behavior, regardless of whether the vehicles are human-driven or Connected Autonomous Vehicles (CAVs). Road signs indicate locally active rules, such as speed limits and requirements to yield or stop. Recent research has demonstrated attacks, such as adding stickers or projected colored patches to signs, that cause CAV misinterpretation, resulting in potential safety issues. Humans can see and potentially defend against these attacks. But humans can not detect what they can not observe. We have developed an effective physical-world attack that leverages the sensitivity of filterless image sensors and the properties of Infrared Laser Reflections (ILRs), which are invisible to humans. The attack is designed to affect CAV cameras and perception, undermining traffic sign recognition by inducing misclassification. In this work, we formulate the threat model and requirements for an ILR-based traffic sign perception attack to succeed. We evaluate the effectiveness of the ILR attack with real-world experiments against two major traffic sign recognition architectures on four IR-sensitive cameras. Our black-box optimization methodology allows the attack to achieve up to a 100% attack success rate in indoor, static scenarios and a >80.5% attack success rate in our outdoor, moving vehicle scenarios. We find the latest state-of-the-art certifiable defense is ineffective against ILR attacks as it mis-certifies >33.5% of cases. To address this, we propose a detection strategy based on the physical properties of IR laser reflections which can detect 96% of ILR attacks.

Thomas Monninger, Shaoyuan Xie, Qi Alfred Chen et al.

The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail scenarios. However, existing methods typically feed LLMs with tokens from multi-view and multi-frame images independently, leading to redundant computation and limited spatial consistency. This separation in visual processing hinders accurate 3D spatial reasoning and fails to maintain geometric coherence across views. On the other hand, Bird's-Eye View (BEV) representations learned from geometrically annotated tasks (e.g., object detection) provide spatial structure but lack the semantic richness of foundation vision encoders. To bridge this gap, we propose BEVLM, a framework that connects a spatially consistent and semantically distilled BEV representation with LLMs. Through extensive experiments, we show that BEVLM enables LLMs to reason more effectively in cross-view driving scenes, improving accuracy by 46%, by leveraging BEV features as unified inputs. Furthermore, by distilling semantic knowledge from LLMs into BEV representations, BEVLM significantly improves closed-loop end-to-end driving performance by 29% in safety-critical scenarios.

Chen Ma, Ningfei Wang, Junhao Zheng et al.

Traffic Sign Recognition (TSR) systems play a critical role in Autonomous Driving (AD) systems, enabling real-time detection of road signs, such as STOP and speed limit signs. While these systems are increasingly integrated into commercial vehicles, recent research has exposed their vulnerability to physical-world adversarial appearance attacks. In such attacks, carefully crafted visual patterns are misinterpreted by TSR models as legitimate traffic signs, while remaining inconspicuous or benign to human observers. However, existing adversarial appearance attacks suffer from notable limitations. Pixel-level perturbation-based methods often lack stealthiness and tend to overfit to specific surrogate models, resulting in poor transferability to real-world TSR systems. On the other hand, text-to-image (T2I) diffusion model-based approaches demonstrate limited effectiveness and poor generalization to out-of-distribution sign types. In this paper, we present DiffSign, a novel T2I-based appearance attack framework designed to generate physically robust, highly effective, transferable, practical, and stealthy appearance attacks against TSR systems. To overcome the limitations of prior approaches, we propose a carefully designed attack pipeline that integrates CLIP-based loss and masked prompts to improve attack focus and controllability. We also propose two novel style customization methods to guide visual appearance and improve out-of-domain traffic sign attack generalization and attack stealthiness. We conduct extensive evaluations of DiffSign under varied real-world conditions, including different distances, angles, light conditions, and sign categories. Our method achieves an average physical-world attack success rate of 83.3%, leveraging DiffSign's high effectiveness in attack transferability.

Chen Ma, Ningfei Wang, Zhengyu Zhao et al.

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%.

Chen Ma, Ningfei Wang, Zhengyu Zhao et al.

Autonomous Driving (AD) systems critically depend on visual perception for real-time object detection and multiple object tracking (MOT) to ensure safe driving. However, high latency in these visual perception components can lead to significant safety risks, such as vehicle collisions. While previous research has extensively explored latency attacks within the digital realm, translating these methods effectively to the physical world presents challenges. For instance, existing attacks rely on perturbations that are unrealistic or impractical for AD, such as adversarial perturbations affecting areas like the sky, or requiring large patches that obscure most of a camera's view, thus making them impossible to be conducted effectively in the real world. In this paper, we introduce SlowPerception, the first physical-world latency attack against AD perception, via generating projector-based universal perturbations. SlowPerception strategically creates numerous phantom objects on various surfaces in the environment, significantly increasing the computational load of Non-Maximum Suppression (NMS) and MOT, thereby inducing substantial latency. Our SlowPerception achieves second-level latency in physical-world settings, with an average latency of 2.5 seconds across different AD perception systems, scenarios, and hardware configurations. This performance significantly outperforms existing state-of-the-art latency attacks. Additionally, we conduct AD system-level impact assessments, such as vehicle collisions, using industry-grade AD systems with production-grade AD simulators with a 97% average rate. We hope that our analyses can inspire further research in this critical domain, enhancing the robustness of AD systems against emerging vulnerabilities.

Takami Sato, Qi Alfred Chen

After the 2017 TuSimple Lane Detection Challenge, its dataset and evaluation based on accuracy and F1 score have become the de facto standard to measure the performance of lane detection methods. While they have played a major role in improving the performance of lane detection methods, the validity of this evaluation method in downstream tasks has not been adequately researched. In this study, we design 2 new driving-oriented metrics for lane detection: End-to-End Lateral Deviation metric (E2E-LD) is directly formulated based on the requirements of autonomous driving, a core downstream task of lane detection; Per-frame Simulated Lateral Deviation metric (PSLD) is a lightweight surrogate metric of E2E-LD. To evaluate the validity of the metrics, we conduct a large-scale empirical study with 4 major types of lane detection approaches on the TuSimple dataset and our newly constructed dataset Comma2k19-LD. Our results show that the conventional metrics have strongly negative correlations ($\leq$-0.55) with E2E-LD, meaning that some recent improvements purely targeting the conventional metrics may not have led to meaningful improvements in autonomous driving, but rather may actually have made it worse by overfitting to the conventional metrics. As autonomous driving is a security/safety-critical system, the underestimation of robustness hinders the sound development of practical lane detection models. We hope that our study will help the community achieve more downstream task-aware evaluations for lane detection.

Sumaya Almanee, Xiafa Wu, Yuqi Huai et al.

There is tremendous global enthusiasm for research, development, and deployment of autonomous vehicles (AVs), e.g., self-driving taxis and trucks from Waymo and Baidu. The current practice for testing AVs uses virtual tests-where AVs are tested in software simulations-since they offer a more efficient and safer alternative compared to field operational tests. Specifically, search-based approaches are used to find particularly critical situations. These approaches provide an opportunity to automatically generate tests; however, systematically creating valid and effective tests for AV software remains a major challenge. To address this challenge, we introduce scenoRITA, a test generation approach for AVs that uses evolutionary algorithms with (1) a novel gene representation that allows obstacles to be fully mutable, hence, resulting in more reported violations, (2) 5 test oracles to determine both safety and motion sickness-inducing violations, and (3) a novel technique to identify and eliminate duplicate tests. Our extensive evaluation shows that scenoRITA can produce effective driving scenarios that expose an ego car to safety critical situations. scenoRITA generated tests that resulted in a total of 1,026 unique violations, increasing the number of reported violations by 23.47% and 24.21% compared to random test generation and state-of-the-art partially-mutable test generation, respectively.

Takami Sato, Qi Alfred Chen

After the 2017 TuSimple Lane Detection Challenge, its evaluation based on accuracy and F1 score has become the de facto standard to measure the performance of lane detection methods. In this work, we conduct the first large-scale empirical study to evaluate the robustness of state-of-the-art lane detection methods under physical-world adversarial attacks in autonomous driving. We evaluate 4 major types of lane detection approaches with the conventional evaluation and end-to-end evaluation in autonomous driving scenarios and then discuss the security proprieties of each lane detection model. We demonstrate that the conventional evaluation fails to reflect the robustness in end-to-end autonomous driving scenarios. Our results show that the most robust model on the conventional metrics is the least robust in the end-to-end evaluation. Although the competition dataset and its metrics have played a substantial role in developing performant lane detection methods along with the rapid development of deep neural networks, the conventional evaluation is becoming obsolete and the gap between the metrics and practicality is critical. We hope that our study will help the community make further progress in building a more comprehensive framework to evaluate lane detection models.

Ruochen Jiao, Hengyi Liang, Takami Sato et al.

In the development of advanced driver-assistance systems (ADAS) and autonomous vehicles, machine learning techniques that are based on deep neural networks (DNNs) have been widely used for vehicle perception. These techniques offer significant improvement on average perception accuracy over traditional methods, however, have been shown to be susceptible to adversarial attacks, where small perturbations in the input may cause significant errors in the perception results and lead to system failure. Most prior works addressing such adversarial attacks focus only on the sensing and perception modules. In this work, we propose an end-to-end approach that addresses the impact of adversarial attacks throughout perception, planning, and control modules. In particular, we choose a target ADAS application, the automated lane centering system in OpenPilot, quantify the perception uncertainty under adversarial attacks, and design a robust planning and control module accordingly based on the uncertainty analysis. We evaluate our proposed approach using both the public dataset and production-grade autonomous driving simulator. The experiment results demonstrate that our approach can effectively mitigate the impact of adversarial attacks and can achieve 55% to 90% improvement over the original OpenPilot.

Jiachen Sun, Karl Koenig, Yulong Cao et al.

3D point clouds play pivotal roles in various safety-critical applications, such as autonomous driving, which desires the underlying deep neural networks to be robust to adversarial perturbations. Though a few defenses against adversarial point cloud classification have been proposed, it remains unknown whether they are truly robust to adaptive attacks. To this end, we perform the first security analysis of state-of-the-art defenses and design adaptive evaluations on them. Our 100% adaptive attack success rates show that current countermeasures are still vulnerable. Since adversarial training (AT) is believed as the most robust defense, we present the first in-depth study showing how AT behaves in point cloud classification and identify that the required symmetric function (pooling operation) is paramount to the 3D model's robustness under AT. Through our systematic analysis, we find that the default-used fixed pooling (e.g., MAX pooling) generally weakens AT's effectiveness in point cloud classification. Interestingly, we further discover that sorting-based parametric pooling can significantly improve the models' robustness. Based on above insights, we propose DeepSym, a deep symmetric pooling operation, to architecturally advance the robustness to 47.0% under AT without sacrificing nominal accuracy, outperforming the original design and a strong baseline by 28.5% ($\sim 2.6 \times$) and 6.5%, respectively, in PointNet.

Takami Sato, Junjie Shen, Ningfei Wang et al.

Automated Lane Centering (ALC) systems are convenient and widely deployed today, but also highly security and safety critical. In this work, we are the first to systematically study the security of state-of-the-art deep learning based ALC systems in their designed operational domains under physical-world adversarial attacks. We formulate the problem with a safety-critical attack goal, and a novel and domain-specific attack vector: dirty road patches. To systematically generate the attack, we adopt an optimization-based approach and overcome domain-specific design challenges such as camera frame inter-dependencies due to attack-influenced vehicle control, and the lack of objective function design for lane detection models. We evaluate our attack on a production ALC using 80 scenarios from real-world driving traces. The results show that our attack is highly effective with over 97.5% success rates and less than 0.903 sec average success time, which is substantially lower than the average driver reaction time. This attack is also found (1) robust to various real-world factors such as lighting conditions and view angles, (2) general to different model designs, and (3) stealthy from the driver's view. To understand the safety impacts, we conduct experiments using software-in-the-loop simulation and attack trace injection in a real vehicle. The results show that our attack can cause a 100% collision rate in different scenarios, including when tested with common safety features such as automatic emergency braking. We also evaluate and discuss defenses.

Jiachen Sun, Yulong Cao, Qi Alfred Chen et al.

Perception plays a pivotal role in autonomous driving systems, which utilizes onboard sensors like cameras and LiDARs (Light Detection and Ranging) to assess surroundings. Recent studies have demonstrated that LiDAR-based perception is vulnerable to spoofing attacks, in which adversaries spoof a fake vehicle in front of a victim self-driving car by strategically transmitting laser signals to the victim's LiDAR sensor. However, existing attacks suffer from effectiveness and generality limitations. In this work, we perform the first study to explore the general vulnerability of current LiDAR-based perception architectures and discover that the ignored occlusion patterns in LiDAR point clouds make self-driving cars vulnerable to spoofing attacks. We construct the first black-box spoofing attack based on our identified vulnerability, which universally achieves around 80% mean success rates on all target models. We perform the first defense study, proposing CARLO to mitigate LiDAR spoofing attacks. CARLO detects spoofed data by treating ignored occlusion patterns as invariant physical features, which reduces the mean attack success rate to 5.5%. Meanwhile, we take the first step towards exploring a general architecture for robust LiDAR-based perception, and propose SVF that embeds the neglected physical features into end-to-end learning. SVF further reduces the mean attack success rate to around 2.3%.

Junjie Shen, Jun Yeon Won, Zeyuan Chen et al.

For high-level Autonomous Vehicles (AV), localization is highly security and safety critical. One direct threat to it is GPS spoofing, but fortunately, AV systems today predominantly use Multi-Sensor Fusion (MSF) algorithms that are generally believed to have the potential to practically defeat GPS spoofing. However, no prior work has studied whether today's MSF algorithms are indeed sufficiently secure under GPS spoofing, especially in AV settings. In this work, we perform the first study to fill this critical gap. As the first study, we focus on a production-grade MSF with both design and implementation level representativeness, and identify two AV-specific attack goals, off-road and wrong-way attacks. To systematically understand the security property, we first analyze the upper-bound attack effectiveness, and discover a take-over effect that can fundamentally defeat the MSF design principle. We perform a cause analysis and find that such vulnerability only appears dynamically and non-deterministically. Leveraging this insight, we design FusionRipper, a novel and general attack that opportunistically captures and exploits take-over vulnerabilities. We evaluate it on 6 real-world sensor traces, and find that FusionRipper can achieve at least 97% and 91.3% success rates in all traces for off-road and wrong-way attacks respectively. We also find that it is highly robust to practical factors such as spoofing inaccuracies. To improve the practicality, we further design an offline method that can effectively identify attack parameters with over 80% average success rates for both attack goals, with the cost of at most half a day. We also discuss promising defense directions.

Zhenyuan Li, Qi Alfred Chen, Runqing Yang et al.

With the development of information technology, the border of the cyberspace gets much broader, exposing more and more vulnerabilities to attackers. Traditional mitigation-based defence strategies are challenging to cope with the current complicated situation. Security practitioners urgently need better tools to describe and modelling attacks for defence. The provenance graph seems like an ideal method for threat modelling with powerful semantic expression ability and attacks historic correlation ability. In this paper, we firstly introduce the basic concepts about system-level provenance graph and proposed typical system architecture for provenance graph-based threat detection and investigation. A comprehensive provenance graph-based threat detection system can be divided into three modules, namely, "data collection module", "data management module", and "threat detection modules". Each module contains several components and involves many research problem. We systematically analyzed the algorithms and design details involved. By comparison, we give the strategy of technology selection. Moreover, we pointed out the shortcomings of the existing work for future improvement.

Takami Sato, Junjie Shen, Ningfei Wang et al.

Lane-Keeping Assistance System (LKAS) is convenient and widely available today, but also extremely security and safety critical. In this work, we design and implement the first systematic approach to attack real-world DNN-based LKASes. We identify dirty road patches as a novel and domain-specific threat model for practicality and stealthiness. We formulate the attack as an optimization problem, and address the challenge from the inter-dependencies among attacks on consecutive camera frames. We evaluate our approach on a state-of-the-art LKAS and our preliminary results show that our attack can successfully cause it to drive off lane boundaries within as short as 1.3 seconds.

Yulong Cao, Chaowei Xiao, Benjamin Cyr et al.

In Autonomous Vehicles (AVs), one fundamental pillar is perception, which leverages sensors like cameras and LiDARs (Light Detection and Ranging) to understand the driving environment. Due to its direct impact on road safety, multiple prior efforts have been made to study its the security of perception systems. In contrast to prior work that concentrates on camera-based perception, in this work we perform the first security study of LiDAR-based perception in AV settings, which is highly important but unexplored. We consider LiDAR spoofing attacks as the threat model and set the attack goal as spoofing obstacles close to the front of a victim AV. We find that blindly applying LiDAR spoofing is insufficient to achieve this goal due to the machine learning-based object detection process. Thus, we then explore the possibility of strategically controlling the spoofed attack to fool the machine learning model. We formulate this task as an optimization problem and design modeling methods for the input perturbation function and the objective function. We also identify the inherent limitations of directly solving the problem using optimization and design an algorithm that combines optimization and global sampling, which improves the attack success rates to around 75%. As a case study to understand the attack impact at the AV driving decision level, we construct and evaluate two attack scenarios that may damage road safety and mobility. We also discuss defense directions at the AV system, sensor, and machine learning model levels.

Yunhan Jia, Yantao Lu, Junjie Shen et al.

Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models. However, in such visual perception pipeline the detected objects must also be tracked, in a process called Multiple Object Tracking (MOT), to build the moving trajectories of surrounding obstacles. Since MOT is designed to be robust against errors in object detection, it poses a general challenge to existing attack techniques that blindly target objection detection: we find that a success rate of over 98% is needed for them to actually affect the tracking results, a requirement that no existing attack technique can satisfy. In this paper, we are the first to study adversarial machine learning attacks against the complete visual perception pipeline in autonomous driving, and discover a novel attack technique, tracker hijacking, that can effectively fool MOT using AEs on object detection. Using our technique, successful AEs on as few as one single frame can move an existing object in to or out of the headway of an autonomous vehicle to cause potential safety hazards. We perform evaluation using the Berkeley Deep Drive dataset and find that on average when 3 frames are attacked, our attack can have a nearly 100% success rate while attacks that blindly target object detection only have up to 25%.

Yunhan Jack Jia, Ding Zhao, Qi Alfred Chen et al.

The advancement in Autonomous Vehicles (AVs) has created an enormous market for the development of self-driving functionalities,raising the question of how it will transform the traditional vehicle development process. One adventurous proposal is to open the AV platform to third-party developers, so that AV functionalities can be developed in a crowd-sourcing way, which could provide tangible benefits to both automakers and end users. Some pioneering companies in the automotive industry have made the move to open the platform so that developers are allowed to test their code on the road. Such openness, however, brings serious security and safety issues by allowing untrusted code to run on the vehicle. In this paper, we introduce the concept of an Appified AV platform that opens the development framework to third-party developers. To further address the safety challenges, we propose an enhanced appified AV design schema called AVGuard, which focuses primarily on mitigating the threats brought about by untrusted code, leveraging theory in the vehicle evaluation field, and conducting program analysis techniques in the cybersecurity area. Our study provides guidelines and suggested practice for the future design of open AV platforms.