Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving
Explore this paper's citation graph
Summary
This work performs the first security study of LiDAR-based perception in AV settings, and designs an algorithm that combines optimization and global sampling, which improves the attack success rates to around 75%.
- Type
- article
- Published
- 2019-07-16
- Cited by
- 682
- References
- 55
- Access
- Open access
- OpenAlex
- https://openalex.org/W2959364614
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:196831979
Keywords
Spoofing attack, Perception, Set (abstract data type), Adversarial system, Situation awareness
References
- Security and Privacy Vulnerabilities of In-Car Wireless Networks: A Tire Pressure Monitoring System Case Study
- Comprehensive Experimental Analyses of Automotive Attack Surfaces
- Attack-resilient sensor fusion
- PyCRA: Physical Challenge-Response Authentication For Active Sensors Under Spoofing Attacks
- Experimental Security Analysis of a Modern Automobile
- Hidden Voice Commands
- A Security Analysis of an In-Vehicle Infotainment and App Platform
- Towards Evaluating the Robustness of Neural Networks
- Error Handling of In-vehicle Networks Makes Them Vulnerable
- Practical Black-Box Attacks against Machine Learning
- Adversarial Examples for Semantic Segmentation and Object Detection
- Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Houdini: Fooling Deep Structured Prediction Models
- Can you fool AI with adversarial examples on a visual Turing test?
- Robust Physical-World Attacks on Deep Learning Models
- Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
- Generating Adversarial Examples with Adversarial Networks
- Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
- Spatially Transformed Adversarial Examples
Cited by
- Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
- Enhancing ML Robustness Using Physical-World Constraints
- AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos
- Rearchitecting Classification Frameworks For Increased Robustness
- Robust Gabor Networks
- Geometry-aware Generation of Adversarial and Cooperative Point Clouds
- Robust Adversarial Objects against Deep Learning Models
- Detecting Deception Attacks on Autonomous Vehicles via Linear Time-Varying Dynamic Watermarking
- GhostImage: Perception Domain Attacks against Vision-based Object Classification Systems
- A Survey of Simultaneous Localization and Mapping
- Adversarial Attacks and Defenses on Cyber–Physical Systems: A Survey
- Phantom of the ADAS: Phantom Attacks on Driver-Assistance Systems
- Gabor Layers Enhance Network Robustness
- Physically Realizable Adversarial Examples for LiDAR Object Detection
- Scalable Autonomous Vehicle Safety Validation through Dynamic Programming and Scene Decomposition
- Geometry-Aware Generation of Adversarial Point Clouds
- ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds
- Mitigating Advanced Adversarial Attacks with More Advanced Gradient Obfuscation Techniques
- Self-Robust 3D Point Recognition via Gather-Vector Guidance
- Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems
Related papers
No related papers recorded.