MIRAGE: Detecting Fake Emergency Electronic Brake Light Attacks in V2X Networks...
summary
MIRAGE is an event-gated detector that activates only on EEBL flags, computes position-derived speed to catch discrepancies and detects post-attack position-freezing artifacts, then bounds the ego response using the Intelligent Driver Model. It is implemented in the V2X Application Spoofing Platform (VASP) and tested against two fake-EEBL variants and three existing defenses, achieving F1 0.922 with 88.3% detection at 0.9% false positive rate and reduces mean braking severity by 75%.
AI-written summary · about
chapters (10)
- 0:00MIRAGE introduction
- 1:35Emergency Brake Light in V2X
- 3:05Fake EBL attacks and gaps
- 5:39Threat model and priorities
- 7:52Why existing detectors fail
- 9:38Event-gated inspection
- 11:48MIRAGE framework overview
- 13:11Post-event behavior analysis
- 15:20Performance comparison
- 16:47Conclusion and future work
related talks
40mSecuring Tesla and Mobileye from Split-Second Phantom Attacks
12mStopping V2X Threats at the Source: Hardware Cybersecurity for Automotive
01h 06mSelf-Driving and Connected Cars: Fooling Sensors and Tracking Drivers
31mMirage: Cyber Deception Against Autonomous Cyber Attacks
14mStateful Behavior Inference and Runtime Enforcement for Vehicle Network Security
13mWIP: Learning Adversarial Attacks on Adaptive Traffic Signal Control Systems...
43mConnected Cars - What could possibly go wrong?
09mLightning Talk: On-Road Driver Identification Dataset with CyberAttack