red mirror counter ai ai
play

Red Mirror: Counter AI AI UDT 2020, Rotterdam Ahoy, NL 27 th May - PowerPoint PPT Presentation

Red Mirror: Counter AI AI UDT 2020, Rotterdam Ahoy, NL 27 th May 2020 COMMERCIAL IN CONFIDENCE Agenda Background Genesis Concept Approach Architecture Testing Red AIs Results ESRA DR SO Prediction


  1. Red Mirror: Counter AI AI UDT 2020, Rotterdam Ahoy, NL 27 th May 2020 COMMERCIAL IN CONFIDENCE

  2. Agenda • Background – Genesis – Concept • Approach – Architecture – Testing – Red AIs • Results – ESRA – DR SO • Prediction accuracy • Identifying unknowns • Next steps COMMERCIAL IN CONFIDENCE Page 2

  3. Background | Genesis • If you can explain our AI, can you predict their AI? COMMERCIAL IN CONFIDENCE Page 3

  4. Background | Concept • Aims – Use a combination of Artificial Intelligence (AI) and Machine Learning (ML) techniques to automatically generate a ‘mirror’ of Red’s AI i.e. the AI controlling enemy vessels • Outputs – Predict Red’s next Courses Of Action (COA) – Identify what Red knows that Blue does not – Identify what Blue knows that Red does not – Suggest what Blue should do to build a better Red Mirror (incl ‘he knows we know he knows…’ effects) – Explain the Red-AI behaviour so that the Intelligent Core or human decision-maker can check whether the Red-AI may be trying to double-bluff • Potential use-cases – Turning Red’s assets into a form of ‘sensor input’ for Blue – Getting ahead of Red i.e. SUPA loop… COMMERCIAL IN CONFIDENCE Page 4

  5. Background | Concept COMMERCIAL IN CONFIDENCE Page 5

  6. Approach | Architecture COMMERCIAL IN CONFIDENCE Page 6

  7. Approach | Testing • Measures of performance – Accuracy of predicting Red’s next COA • Over time/observations • By specific action • By degree – Uncertainty of prediction • By probability • By degree – Accuracy of identifying what Red knows that Blue does not – Accuracy of identifying what Red knows that Blue does not • Test cases – Different ‘ Red AIs’ • ESRA • DR SO – Knowledge • Full • Full for Red not for Blue • Full for Blue not for Red COMMERCIAL IN CONFIDENCE Page 7

  8. Approach | Red AIs • ESRA – 1 red ship avoiding and destroying 8 blue missiles) Threat_L Bearing Speed_ No_Of_ Missile_ Type_Of Missile_ evel_Of_ _Of_Mis Of_Miss Engaged Course_Of_Action Tracks Number _Missile Missile sile ile 4 7 0.5 300 KH-35U 434 7 HK1 track 0 4 8 0.4 30 KH-35U 434 8 SK0 track 0 4 5 0.7 30 KH-31A 600 5 HK1 track 0 4 8 0.3 120 KH-35U 434 N/A Wait COMMERCIAL IN CONFIDENCE Page 8

  9. Approach | Red AIs • DR SO – 4 Red agents chasing 1 Blue agent, around obstacles COMMERCIAL IN CONFIDENCE Page 9

  10. Results | ESRA – prediction accuracy vs categorical outputs COMMERCIAL IN CONFIDENCE Page 10

  11. Results | DR SO – prediction accuracy vs continuous outputs COMMERCIAL IN CONFIDENCE Page 11

  12. Results | DR SO – confidence in prediction accuracy COMMERCIAL IN CONFIDENCE Page 12

  13. Results | DR SO – what Blue does not know COMMERCIAL IN CONFIDENCE Page 13

  14. Next steps • Short-term – Demonstrate the operational impact of the demonstrated prediction accuracy, and accuracy of identifying the Blue or Red unknown e.g. • How much extra time does the Blue agent get before the DR SO Red agents successfully surround or swarm it? • How much does the Blue probability of success increase against a Red AD platform using ESRA, in terms of kill probability or rate of reduction of Red stocks? – Test a ‘reverse - decision tree’ or ‘reverse random forest’ method for identifying unknown information to improve the balance between accuracy of identification and FPR – Testing methods for extracting, or back calculating, the reward structure of the Red AI, which is implicit in the Red Mirror • Medium-term – Wider project to explore some of the issues more deeply e.g. • What types of Red AI we would wish to apply the Red Mirror concept to and what benefits accrue? • How is the difficulty of predicting AI COAs driven by the COAs and the scenarios it is used in? • Why might it be correct to not use all the past observations to predict Red, and how might the threshold after which past data is useful be found? • Why might partial knowledge improve short-term prediction accuracy but worsen longer-term prediction accuracy? • How might deception be exploited in counter-AI activity? COMMERCIAL IN CONFIDENCE Page 14

Recommend


More recommend