Toward Physical-Layer Fingerprinting of Production Automotive...
summary
Claims physical-layer CAN fingerprints separate identical units by manufacturing variation, validated on bench dev boards and on nine identical production ECUs measured across days and sessions. Uses analog CAN waveforms, extracts baseline, slew rate, overshoot, ringing frequency, settling time and feeds a hybrid model that achieves 99.5% accuracy in real time on development boards and reliably distinguishes cloned production ECUs. Captures done across sessions show fingerprint stability.
AI-written summary · about
related talks
30mFingerprinting Electronic Control Units for Vehicle Intrusion Detection
11mWIP: Intrusion Detection and Localization for CAN by Extracting Propagation Delay..
50mSensor and Process Fingerprinting in Industrial Control Systems
16mWIP: A Black Box System for Automotive Digital Forensics
41mIt's easier to break than to patch: a stealthy DoS attack on CAN
46mPASTA: Portable Automotive Security Testbed with Adaptability
50mAdvanced CAN Injection Techniques for Vehicle Networks
14mStateful Behavior Inference and Runtime Enforcement for Vehicle Network Security