US 12,438,890 B2
Attack detection and countermeasures for autonomous navigation
Md Tanvir Arafin, Baltimore, MD (US); and Kevin Kornegay, Towson, MD (US)
Assigned to MORGAN STATE UNIVERSITY, Baltimore, MD (US)
Filed by Morgan State University, Baltimore, MD (US)
Filed on Jul. 18, 2023, as Appl. No. 18/223,302.
Claims priority of provisional application 63/343,184, filed on May 18, 2022.
Prior Publication US 2024/0214394 A1, Jun. 27, 2024
Int. Cl. H04L 9/40 (2022.01); G01S 19/00 (2010.01); G01S 19/21 (2010.01); G01S 19/25 (2010.01)
CPC H04L 63/14 (2013.01) [H04L 9/40 (2022.05); G01S 19/00 (2013.01); G01S 19/21 (2013.01); G01S 19/215 (2013.01); G01S 19/25 (2013.01); G01S 19/256 (2013.01)] 2 Claims
OG exemplary drawing
 
1. A method for detecting a replay attack on an autonomous navigation system and surviving said replay attack, comprising:
using two or more stereo image sensors mounted in an autonomous vehicle to collect primary pose data for said autonomous vehicle, using inertial measurement units mounted in said autonomous vehicle to collect secondary pose date for said autonomous vehicle,
sending said primary data and said secondary data to a neural network,
using an open-loop shallow neural network-based nonlinear autoregressive exogenous model on said neural network to train drift estimation between said primary pose data and said secondary pose data; and
using a closed-loop model on said neural network for multi-step prediction of pose drift y(t) between said primary pose data and said secondary pose data based on the equation:

OG Complex Work Unit Math
wherein said neural network comprises a predefined threshold modeling error and a predefined temporal window for assessing anomalous events;
said method further comprising implementing attack survival steps when error E(t) exceeds said predefined threshold modeling error, said attack survival steps including termination of autonomous driving.