US 12,423,416 B2
Stealthy process attack detection for automated manufacturing
Joel A. Dawson, Oak Ridge, TN (US); Srikanth B. Yoginath, Knoxville, TN (US); Michael D. Iannacone, Oak Ridge, TN (US); Varisara Tansakul, Knoxville, TN (US); Ali Passian, Knoxville, TN (US); Milton N. Ericson, Knoxville, TN (US); Gavin B. Long, Knoxville, TN (US); Robert C. Jordan, Clinton, TN (US); and Joel M. Asiamah, Knoxville, TN (US)
Assigned to UT-Battelle, LLC, Oak Ridge, TN (US)
Filed by UT-Battelle, LLC, Oak Ridge, TN (US)
Filed on Oct. 19, 2023, as Appl. No. 18/381,735.
Claims priority of provisional application 63/417,358, filed on Oct. 19, 2022.
Prior Publication US 2024/0134969 A1, Apr. 25, 2024
Int. Cl. G06F 21/54 (2013.01); B29C 64/393 (2017.01); B33Y 50/02 (2015.01); G06F 21/55 (2013.01)
CPC G06F 21/54 (2013.01) [B29C 64/393 (2017.08); B33Y 50/02 (2014.12); G06F 21/552 (2013.01)] 20 Claims
OG exemplary drawing
 
1. Memory encoding instructions that, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising:
accessing current and voltage signals indicative of instructions provided by controller circuitry of a 3D printer to actuators thereof based on a toolpath source, wherein subsets of the accessed current and voltage signals correspond to unaltered instructions and to instructions altered by malicious changes to the toolpath source;
retrieving respective phase signals from the current and voltage signals of the subsets;
determining phase synchrony metrics between the phase signals in a pair-wise manner, and associate, based on the phase synchrony metrics, a first class of signals with unaltered instructions and a second class of signals with altered instructions;
training, based on the determined phase synchrony metrics between the phase signals retrieved from the current and/or voltage signals indicative of instructions to at least some of the actuators, a Bayesian probabilistic model of logistic regression to define the boundary between the first class and the second class;
receiving a new current or voltage signal indicative of new instructions provided by the controller circuitry to one of the actuators; and
predicting, based on the trained model, whether the new instructions are unaltered or altered.