AVstack: An Open-Source, Reconfigurable Platform for Autonomous Vehicle Development

Hallyburton, R. Spencer; Zhang, Shucheng; Pajić, Miroslav

doi:10.1145/3576841.3585930

Cited by 2 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intuitively, MadRadar attacks achieve a FN outcome by adding clutter in the Range-Doppler response around a specific target, in order to raise the CA-CFAR detection threshold and thus significantly decrease the probability of the actual target being detected. We start with the FP attack signal from (10) that spoofs a false object at the same range and velocity as an actual target. Next, we slightly smear the spoofed signal in the range domain by using a very similar slope ( S ′ ) that is slightly offset (∼0.01 MHz/µs) from the estimated victim slope ( S).…”

Section: False Negative Attacksmentioning

confidence: 99%

“…The translation attack is achieved by simultaneously transmitting the FP attack from (10) and the FN attack from (11). For the FN attack, we set d spoof and v spoof to the location of an actual target so that it is 'removed' from the victim radar's point cloud.…”

Section: Translation Attackmentioning

confidence: 99%

“…The MadRadar prototype, in real-time, estimates the victim radar's chirp slope ( S), chirp period ( T chirp ), and frame duration ( T frame ) as described in Section IV. Based on the estimated parameters, the attacker designs and transmits the corresponding signal for launching a FP, FN, or translation attack using (10) and (11). The MadRadar prototype is the first to demonstrate the feasibility of launching real-time blackbox FP, FN, and translation attacks on a real-world system.…”

Section: A Implementation On An Sdr Platformmentioning

confidence: 99%

“…14 Translation attack. Here, we simultaneously launched the FN attack from (11) and FP attack from (10). The FN attack was launched with d spoof and v spoof set to 75 m and -5 m/s, respectively.…”

Section: Setupmentioning

confidence: 99%

“…While there are a plethora of analyses for camera and LiDAR (light detection and ranging) vulnerabilities in autonomous vehicles (e.g., [6]- [10]), automotive radars have only recently started to attract attention in the security community. Existing security research dealing with physical layer (PHY) attacks on FMCW radar systems has solely focused on spoofing attacks inserting false points into a victim radar's point cloud -i.e., false positive (FP) attacks.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

MadRadar: A Black-Box Physical Layer Attack Framework on mmWave Automotive FMCW Radars

Hunt,

Angell,

et al. 2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Frequency modulated continuous wave (FMCW) millimeter-wave (mmWave) radars play a critical role in many of the advanced driver assistance systems (ADAS) featured on today's vehicles. While previous works have demonstrated (only) successful false-positive spoofing attacks against these sensors, all but one assumed that an attacker had the runtime knowledge of the victim radar's configuration. In this work, we introduce MadRadar, a general black-box radar attack framework for automotive mmWave FMCW radars capable of estimating the victim radar's configuration in real-time, and then executing an attack based on the estimates. We evaluate the impact of such attacks maliciously manipulating a victim radar's point cloud, and show the novel ability to effectively 'add' (i.e., false positive attacks), 'remove' (i.e., false negative attacks), or 'move' (i.e., translation attacks) object detections from a victim vehicle's scene. Finally, we experimentally demonstrate the feasibility of our attacks on real-world case studies performed using a realtime physical prototype on a software-defined radio platform.

show abstract

Section: False Negative Attacksmentioning

confidence: 99%

Section: Translation Attackmentioning

confidence: 99%

Section: A Implementation On An Sdr Platformmentioning

confidence: 99%

Section: Setupmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

MadRadar: A Black-Box Physical Layer Attack Framework on mmWave Automotive FMCW Radars

Hunt,

Angell,

et al. 2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

show abstract

Simplifying Sim-to-Real Transfer in Autonomous Driving: Coupling Autoware with the CommonRoad Motion Planning Framework

Würsching,

Mascetta,

Lin

et al. 2024

2024 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Validating motion planning algorithms for autonomous vehicles on a real system is essential to improve their safety in the real world. Open-source initiatives, such as Autoware, provide a deployable software stack for real vehicles. However, such driving stacks have a high entry barrier, so that integrating new algorithms is tedious. Especially new research results are thus mostly evaluated only in simulation, e.g., within the CommonRoad benchmark suite. To address this problem, we present CR2AW, a publicly available interface between the CommonRoad framework and Autoware. CR2AW significantly simplifies the sim-to-real transfer of motion planning research, by allowing users to easily integrate their CommonRoad planning modules into Autoware. Our experiments both in simulation and on our research vehicle showcase the usefulness of CR2AW.

show abstract

AVstack: An Open-Source, Reconfigurable Platform for Autonomous Vehicle Development

Cited by 2 publications

References 10 publications

MadRadar: A Black-Box Physical Layer Attack Framework on mmWave Automotive FMCW Radars

MadRadar: A Black-Box Physical Layer Attack Framework on mmWave Automotive FMCW Radars

Simplifying Sim-to-Real Transfer in Autonomous Driving: Coupling Autoware with the CommonRoad Motion Planning Framework

Contact Info

Product

Resources

About