ML24299A161

From kanterella
Jump to navigation Jump to search
Advanced Sensors and Instrumentation Characterizing Nuclear Cybersecurity Using Ai/Ml (Presentation)
ML24299A161
Person / Time
Issue date: 10/25/2024
From: Basturescu S
NRC/RES/DE
To:
Segiu Basturescu 301-415-1237
References
Download: ML24299A161 (10)


Text

Characterizing Nuclear Cybersecurity Using AI/ML Advanced Sensors and Instrumentation (ASI)

Annual Program Webinar November 4, 2024 Acting Branch Chief: Sergiu Basturescu U.S. Nuclear Regulatory Commission

2 Research Overview Research Overview Res ea rch i nto d i gi ta l i n stru mentati o n a n d contro l systems, electrical engineering and cybers ecurity.

Instrumentation & Control R e s e a rc h o n s a fe t y h a za r d i d e n t i f i c a t i o n fo r d i g i t a l c o n t ro l sy s t e m s. P ro v i d e t e c h n i c a l r e s e a rc h t o s u p p o r t l i c e n s i n g d e c i s i o n s fo r m o d e r n d i g i t a l c o n t ro l s a n d i n s t r u m e n t a t i o n.

Electrical Engineering R e s e a rc h a s s o c i a t e d w i t h m o d e r n b a tt e r y t e c h n o l o g i e s, o p e ra t i n g p l a n t s n o t c o n n e c t e d t o t h e e l e c t r i c a l g r i d, a n d e n a b l i n g s a fe o p e ra t i o n d u r i n g l o n g - t e r m ( 6 0 y r + ) p l a n t o p e ra t i o n.

Cybersecurity R e s e a rc h t o e n s u r e t h e p ro t e c t i o n o f c r i t i c a l d i g i t a l a s s e t s a s s o c i a t e d w i t h s a fe t y, s e c u r i t y, a n d e m e r g e n c y p r e p a r e d n e s s f u n c t i o n s a t n u c l e a r fa c i l i t i e s.

3 Project Start: Oct 2022 Project Finish: May 2024 Project Overview Project Overview

4 Identify Nuclear AI-CyS Use Case Data Collection

& Model Training Performance Evaluation &

Gap Analysis Develop &

Document Insights Normal States Off Normal States Cyber Events Normal Operations Other Events Project Overview OBJECTIVES (1) Explore the use of AI/ML to classify nuclear cybersecurity states (2) Develop insights for assessment of nuclear AI-CyS

5 Project Team NRC

  • Kaitlyn Cottrell (AI/ML)
  • Anya Kim (cybersecurity)

Purdue University

  • Prof. Stylianos Chatzidakis (Dir Nuclear Engineering Radiation Lab)
  • 5 graduate students (nuclear, AI, M&S)

6

- Real data

- Algorithm performance

- Data Management Challenges and Insights Example event progression 0

5000 10000 15000 20000 25000 30000 35000 40000 0

20 40 60 80 Null values Features Overall Null Values

- Data artifacts

- Robustness

- Explainability

7 Composite Classifier

8 Reports

  • Research Plan Development (TLR-RES/DE-2024-003a),

ML23040A169

  • Identification of a Representative Use Case (TLR-RES/DE-2024-003b),

ML23062A349

  • Identification of AI-ML Technology (TLR-RES/DE-2024-003c),

ML23102A182

  • Use Case Implementation (TLR-RES/DE-2024-003d), ML24052A002
  • Performance Evaluation and Gap Analysis (TLR-RES/DE-2024-003e),

ML24193A007

  • Final Report: Characterizing Nuclear Cybersecurity States using AI-ML (TLR-RES/DE-2024-003), ML24193A008

9 Future Work concerning Collecting the right data Managing change Understanding the vulnerabilities/ attack vectors introduced by AI Understanding the threat of attackers using AI Integration with humans Trusting AI Impact on NRC regulations and guidance Whats Next?

Whats Next?

Doug Eskins Senior Computer Engineer Instrumentation, Controls, and Electrical Engineering Branch Office of Nuclear Regulatory Research United States Nuclear Regulatory Commission Email: Doug.Eskins@nrc.gov Sergiu Basturescu Acting Branch Chief Instrumentation, Controls, and Electrical Engineering Branch Office of Nuclear Regulatory Research United States Nuclear Regulatory Commission Email: Sergiu.Basturescu@nrc.gov Christopher Cook Branch Chief Instrumentation, Controls, and Electrical Engineering Branch Office of Nuclear Regulatory Research United States Nuclear Regulatory Commission Email: Christopher.Cook@nrc.gov

asi.inl.gov/

energy.gov/ne Thank You