Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Modelling and Verification of Social Explainable AI (2302.01063v2)

Published 2 Feb 2023 in cs.MA

Abstract: Social Explainable AI (SAI) is a new direction in artificial intelligence that emphasises decentralisation, transparency, social context, and focus on the human users. SAI research is still at an early stage. Consequently, it concentrates on delivering the intended functionalities, but largely ignores the possibility of unwelcome behaviours due to malicious or erroneous activity. We propose that, in order to capture the breadth of relevant aspects, one can use models and logics of strategic ability, that have been developed in multi-agent systems. Using the STV model checker, we take the first step towards the formal modelling and verification of SAI environments, in particular of their resistance to various types of attacks by compromised AI modules.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. Formal verification of neural agents in non-deterministic environments. Auton. Agents Multi Agent Syst., 36(1):6, 2022.
  2. Alternating-time Temporal Logic. Journal of the ACM, 49:672–713, 2002.
  3. Efficient neural network verification via layer-based semidefinite relaxations and linear cuts. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, pages 2184–2190. ijcai.org, 2021.
  4. Logics for reasoning about strategic abilities in multi-player games. In J. van Benthem, S. Ghosh, and R. Verbrugge, editors, Models of Strategic Reasoning. Logics, Games, and Communities, volume 8972 of Lecture Notes in Computer Science, pages 93–136. Springer, 2015.
  5. Handbook of Model Checking. Springer, 2018.
  6. The internet of people: A human and data-centric paradigm for the next generation internet. Comput. Commun., 131:51–65, 2018.
  7. Human-ai ecosystem with abrupt changes as a function of the composition. PLOS ONE, 17(5):1–12, 05 2022.
  8. On the security of public key protocols. IEEE Trans. Inf. Theory, 29(2):198–207, 1983.
  9. Federated vs. centralized machine learning under privacy-elastic users: A comparative analysis. In Proceedings of NCA, pages 1–8. IEEE, 2020.
  10. E.A. Emerson. Temporal and modal logic. In J. van Leeuwen, editor, Handbook of Theoretical Computer Science, volume B, pages 995–1072. Elsevier, 1990.
  11. Modeling human behavior part I - learning and belief approaches. CoRR, abs/2205.06485, 2022.
  12. Dieter Gollmann. Computer Security (3. ed.). Wiley, 2011.
  13. Making machine learning robust against adversarial inputs. Commun. ACM, 61(7):56–66, 2018.
  14. Gossip learning as a decentralized alternative to federated learning. In Proceedings of IFIP DAIS, volume 11534 of Lecture Notes in Computer Science, pages 74–90. Springer, 2019.
  15. Decentralized learning works: An empirical comparison of gossip learning and federated learning. J. Parallel Distributed Comput., 148:109–124, 2021.
  16. Towards partial order reductions for strategic ability. Journal of Artificial Intelligence Research, 68:817–850, 2020.
  17. Approximate verification of strategic abilities under imperfect information. Artificial Intelligence, 277, 2019.
  18. Timing attacks on machine learning: State of the art. In Intelligent Systems and Applications - Proceedings of IntelliSys Volume 1, volume 1037 of Advances in Intelligent Systems and Computing, pages 111–125. Springer, 2019.
  19. Towards scalable complete verification of relu neural networks via dependency-based branching. In Proceedings of IJCAI, pages 2643–2650. ijcai.org, 2021.
  20. Adversarial machine learning-industry perspectives. In IEEE Security and Privacy Workshops, pages 69–75. IEEE, 2020.
  21. Damian Kurpiewski. STV – StraTegic Verifier. code repository, 2022. https://github.com/blackbat13/stv.
  22. Verification of Multi-agent Properties in Electronic Voting: A Case Study. In Proceedings of AiML 2022, 2022.
  23. STV+Reductions: Towards practical verification of strategic ability using model reductions. In Proceedings of AAMAS, pages 1770–1772. ACM, 2021.
  24. MCMAS: An open-source model checker for the verification of multi-agent systems. International Journal on Software Tools for Technology Transfer, 19(1):9–30, 2017.
  25. SAI simulator for social AI gossiping, 2022. https://zenodo.org/record/5780042.
  26. Social-aware federated learning: Challenges and opportunities in collaborative data training. IEEE Internet Computing, pages 1–7, 2022.
  27. M. Pauly. A modal logic for coalitional power in games. Journal of Logic and Computation, 12(1):149–166, 2002.
  28. Pierre-Yves Schobbens. Alternating-time logic with imperfect recall. Electronic Notes in Theoretical Computer Science, 85(2):82–93, 2004.
  29. Y. Shoham and K. Leyton-Brown. Multiagent Systems - Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press, 2009.
  30. Social AI gossiping. Micro-project in Humane-AI-Net. Project website, 2022. https://www.ai4europe.eu/research/research-bundles/social-ai-gossiping.
  31. Social Explainable AI, CHIST-ERA. Project website, 2021–24. http://www.sai-project.eu/.
  32. Harnessing the power of ego network layers for link prediction in online social networks. CoRR, abs/2109.09190, 2021.
  33. G. Weiss, editor. Multiagent Systems. A Modern Approach to Distributed Artificial Intelligence. MIT Press: Cambridge, Mass, 1999.
  34. A game-based approximate verification of deep neural networks with provable guarantees. Theor. Comput. Sci., 807:298–329, 2020.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now