Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 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

Checking Trustworthiness of Probabilistic Computations in a Typed Natural Deduction System (2206.12934v3)

Published 26 Jun 2022 in cs.LO and cs.AI

Abstract: In this paper we present the probabilistic typed natural deduction calculus TPTND, designed to reason about and derive trustworthiness properties of probabilistic computational processes, like those underlying current AI applications. Derivability in TPTND is interpreted as the process of extracting $n$ samples of possibly complex outputs with a certain frequency from a given categorical distribution. We formalize trust for such outputs as a form of hypothesis testing on the distance between such frequency and the intended probability. The main advantage of the calculus is to render such notion of trustworthiness checkable. We present a computational semantics for the terms over which we reason and then the semantics of TPTND, where logical operators as well as a Trust operator are defined through introduction and elimination rules. We illustrate structural and metatheoretical properties, with particular focus on the ability to establish under which term evolutions and logical rules applications the notion of trustworhtiness can be preserved.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. A type theory for probabilistic and bayesian reasoning. In Tarmo Uustalu, editor, 21st International Conference on Types for Proofs and Programs, TYPES 2015, May 18-21, 2015, Tallinn, Estonia, volume 69 of LIPIcs, pages 1:1–1:34. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, 2015. doi: 10.4230/LIPIcs.TYPES.2015.1. URL https://doi.org/10.4230/LIPIcs.TYPES.2015.1.
  2. Fairsquare: Probabilistic verification of program fairness. Proc. ACM Program. Lang., 1(OOPSLA), oct 2017. doi: 10.1145/3133904. URL https://doi.org/10.1145/3133904.
  3. Alessandro Aldini. Design and verification of trusted collective adaptive systems. ACM Trans. Model. Comput. Simul., 28(2):9:1–9:27, 2018. doi: 10.1145/3155337. URL https://doi.org/10.1145/3155337.
  4. Logics to reason formally about trust computation and manipulation. In Andrea Saracino and Paolo Mori, editors, Emerging Technologies for Authorization and Authentication - Second International Workshop, ETAA 2019, Luxembourg City, Luxembourg, September 27, 2019, Proceedings, volume 11967 of Lecture Notes in Computer Science, pages 1–15. Springer, 2019. ISBN 978-3-030-39748-7. doi: 10.1007/978-3-030-39749-4\_1. URL https://doi.org/10.1007/978-3-030-39749-4\_1.
  5. Automatic symbolic verification of embedded systems. IEEE Trans. Softw. Eng., 22(3):181–201, mar 1996. ISSN 0098-5589. doi: 10.1109/32.489079. URL https://doi.org/10.1109/32.489079.
  6. Boolean-valued semantics for the stochastic λ𝜆\lambdaitalic_λ-calculus. In Anuj Dawar and Erich Grädel, editors, Proceedings of the 33rd Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2018, Oxford, UK, July 09-12, 2018, pages 669–678. ACM, 2018. doi: 10.1145/3209108.3209175. URL https://doi.org/10.1145/3209108.3209175.
  7. Minimizing transitive trust threats in software management systems. In Ali A. Ghorbani, Vicenç Torra, Hüseyin Hisil, Ali Miri, Ahmet Koltuksuz, Jie Zhang, Murat Sensoy, Joaquín García-Alfaro, and Ibrahim Zincir, editors, 13th Annual Conference on Privacy, Security and Trust, PST 2015, Izmir, Turkey, July 21-23, 2015, pages 191–198. IEEE Computer Society, 2015. ISBN 978-1-4673-7828-4. doi: 10.1109/PST.2015.7232973. URL https://doi.org/10.1109/PST.2015.7232973.
  8. A lambda-calculus foundation for universal probabilistic programming. In Jacques Garrigue, Gabriele Keller, and Eijiro Sumii, editors, Proceedings of the 21st ACM SIGPLAN International Conference on Functional Programming, ICFP 2016, Nara, Japan, September 18-22, 2016, pages 33–46. ACM, 2016. ISBN 978-1-4503-4219-3. doi: 10.1145/2951913.2951942. URL https://doi.org/10.1145/2951913.2951942.
  9. Marija Boričić. Inference rules for probability logic. Publications de l’Institut Mathématique, 100(114):77–86, 2016.
  10. Marija Boričić. Suppes-style sequent calculus for probability logic. Journal of Logic and Computation, 27(4):1157–1168, 2017.
  11. Marija Boričić. Sequent calculus for classical logic probabilized. Archive for Mathematical Logic, 58(1-2):119–136, 2019.
  12. A granular approach to source trustworthiness for negative trust assessment. In Weizhi Meng, Piotr Cofta, Christian Damsgaard Jensen, and Tyrone Grandison, editors, Trust Management XIII - 13th IFIP WG 11.11 International Conference, IFIPTM 2019, Copenhagen, Denmark, July 17-19, 2019, Proceedings, volume 563 of IFIP Advances in Information and Communication Technology, pages 108–121. Springer, 2019. ISBN 978-3-030-33715-5. doi: 10.1007/978-3-030-33716-2\_9. URL https://doi.org/10.1007/978-3-030-33716-2\_9.
  13. Computable trustworthiness ranking of medical experts in italy during the sars-cov-19 pandemic. In Ombretta Gaggi, Pietro Manzoni, and Claudio E. Palazzi, editors, GoodIT ’21: Conference on Information Technology for Social Good, Roma, Italy, September 9-11, 2021, pages 271–276. ACM, 2021. doi: 10.1145/3462203.3475907. URL https://doi.org/10.1145/3462203.3475907.
  14. Byron Cook. Formal reasoning about the security of amazon web services. In Hana Chockler and Georg Weissenbacher, editors, Computer Aided Verification, pages 38–47, Cham, 2018. Springer International Publishing. ISBN 978-3-319-96145-3.
  15. Semantics of higher-order probabilistic programs with conditioning. Proc. ACM Program. Lang., 4(POPL):57:1–57:29, 2020. doi: 10.1145/3371125. URL https://doi.org/10.1145/3371125.
  16. Probabilistic typed natural deduction for trustworthy computations. In Dongxia Wang, Rino Falcone, and Jie Zhang, editors, Proceedings of the 22nd International Workshop on Trust in Agent Societies (TRUST 2021) Co-located with the 20th International Conferences on Autonomous Agents and Multiagent Systems (AAMAS 2021), London, UK, May 3-7, 2021, volume 3022 of CEUR Workshop Proceedings. CEUR-WS.org, 2021. URL http://ceur-ws.org/Vol-3022/paper3.pdf.
  17. Universal semantics for the stochastic λ𝜆\lambdaitalic_λ-calculus. In 36th Annual ACM/IEEE Symposium on Logic in Computer Science, LICS 2021, Rome, Italy, June 29 - July 2, 2021, pages 1–12. IEEE, 2021. ISBN 978-1-6654-4895-6. doi: 10.1109/LICS52264.2021.9470747. URL https://doi.org/10.1109/LICS52264.2021.9470747.
  18. Robert Demolombe. Reasoning about trust: A formal logical framework. In Christian Damsgaard Jensen, Stefan Poslad, and Theodosis Dimitrakos, editors, Trust Management, Second International Conference, iTrust 2004, Oxford, UK, March 29 - April 1, 2004, Proceedings, volume 2995 of Lecture Notes in Computer Science, pages 291–303. Springer, 2004. ISBN 3-540-21312-0. doi: 10.1007/978-3-540-24747-0\_22. URL https://doi.org/10.1007/978-3-540-24747-0\_22.
  19. Alessandra Di Pierro. A type theory for probabilistic–calculus. In From Lambda Calculus to Cybersecurity Through Program Analysis: Essays Dedicated to Chris Hankin on the Occasion of His Retirement, pages 86–102. Springer, 2020.
  20. Reasoning about trust and time in a system of agents. In Elhadi M. Shakshuki, editor, The 8th International Conference on Ambient Systems, Networks and Technologies (ANT 2017) / The 7th International Conference on Sustainable Energy Information Technology (SEIT 2017), 16-19 May 2017, Madeira, Portugal, volume 109 of Procedia Computer Science, pages 632–639. Elsevier, 2017. doi: 10.1016/j.procs.2017.05.369. URL https://doi.org/10.1016/j.procs.2017.05.369.
  21. Specification and automatic verification of trust-based multi-agent systems. Future Gener. Comput. Syst., 107:1047–1060, 2020. doi: 10.1016/j.future.2018.01.040. URL https://doi.org/10.1016/j.future.2018.01.040.
  22. Verifai: A toolkit for the design and analysis of artificial intelligence-based systems, 2019.
  23. Reduced variance deep reinforcement learning with temporal logic specifications. In Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical Systems, ICCPS ’19, pages 237–248, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450362856. doi: 10.1145/3302509.3311053. URL https://doi.org/10.1145/3302509.3311053.
  24. A typed lambda-calculus for establishing trust in probabilistic programs. CoRR, abs/2302.00958, 2023. doi: 10.48550/arXiv.2302.00958. URL https://doi.org/10.48550/arXiv.2302.00958.
  25. Probabilistic reasoning about simply typed lambda terms. In International Symposium on Logical Foundations of Computer Science, pages 170–189. Springer, 2018.
  26. J. Harrison. Formal verification at intel. In 18th Annual IEEE Symposium of Logic in Computer Science, 2003, pages 45–54, 2003. doi: 10.1109/LICS.2003.1210044.
  27. A logic of trust and reputation. Log. J. IGPL, 18(1):214–244, 2010. doi: 10.1093/jigpal/jzp077. URL https://doi.org/10.1093/jigpal/jzp077.
  28. Prism: Probabilistic symbolic model checker. In Proceedings of the 12th International Conference on Computer Performance Evaluation, Modelling Techniques and Tools, TOOLS ’02, pages 200–204, Berlin, Heidelberg, 2002. Springer-Verlag. ISBN 3540435395.
  29. Churn-Jung Liau. Belief, information acquisition, and trust in multi-agent systems–a modal logic formulation. Artif. Intell., 149(1):31–60, 2003. doi: 10.1016/S0004-3702(03)00063-8. URL https://doi.org/10.1016/S0004-3702(03)00063-8.
  30. Reasoning about belief, evidence and trust in a multi-agent setting. In Bo An, Ana L. C. Bazzan, João Leite, Serena Villata, and Leendert W. N. van der Torre, editors, PRIMA 2017: Principles and Practice of Multi-Agent Systems - 20th International Conference, Nice, France, October 30 - November 3, 2017, Proceedings, volume 10621 of Lecture Notes in Computer Science, pages 71–89. Springer, 2017. ISBN 978-3-319-69130-5. doi: 10.1007/978-3-319-69131-2\_5. URL https://doi.org/10.1007/978-3-319-69131-2\_5.
  31. Giuseppe Primiero. A logic of negative trust. J. Appl. Non Class. Logics, 30(3):193–222, 2020. doi: 10.1080/11663081.2020.1789404. URL https://doi.org/10.1080/11663081.2020.1789404.
  32. Managing software uninstall with negative trust. In Jan-Philipp Steghöfer and Babak Esfandiari, editors, Trust Management XI - 11th IFIP WG 11.11 International Conference, IFIPTM 2017, Gothenburg, Sweden, June 12-16, 2017, Proceedings, volume 505 of IFIP Advances in Information and Communication Technology, pages 79–93. Springer, 2017. ISBN 978-3-319-59170-4. doi: 10.1007/978-3-319-59171-1\_7. URL https://doi.org/10.1007/978-3-319-59171-1\_7.
  33. Negative trust for conflict resolution in software management. Web Intell., 16(4):251–271, 2018. doi: 10.3233/WEB-180393. URL https://doi.org/10.3233/WEB-180393.
  34. Proof-checking bias in labeling methods. In Guido Boella, Fabio Aurelio D’Asaro, Abeer Dyoub, and Giuseppe Primiero, editors, Proceedings of 1st Workshop on Bias, Ethical AI, Explainability and the Role of Logic and Logic Programming (BEWARE 2022) co-located with the 21th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2022), Udine, Italy, December 2, 2022, volume 3319 of CEUR Workshop Proceedings, pages 9–19. CEUR-WS.org, 2022. URL https://ceur-ws.org/Vol-3319/paper1.pdf.
  35. A proof-theoretic trust and reputation model for VANET. In 2017 IEEE European Symposium on Security and Privacy Workshops, EuroS&P Workshops 2017, Paris, France, April 26-28, 2017, pages 146–152. IEEE, 2017. ISBN 978-1-5386-2244-5. doi: 10.1109/EuroSPW.2017.64. URL https://doi.org/10.1109/EuroSPW.2017.64.
  36. Formal specification for deep neural networks. In Shuvendu K. Lahiri and Chao Wang, editors, Automated Technology for Verification and Analysis, pages 20–34, Cham, 2018. Springer International Publishing.
  37. Munindar P. Singh. Trust as dependence: a logical approach. In Liz Sonenberg, Peter Stone, Kagan Tumer, and Pinar Yolum, editors, 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), Taipei, Taiwan, May 2-6, 2011, Volume 1-3, pages 863–870. IFAAMAS, 2011. ISBN 978-0-9826571-5-7. URL http://portal.acm.org/citation.cfm?id=2031741\&CFID=54178199\&CFTOKEN=61392764.
  38. Logic and model checking by imprecise probabilistic interpreted systems. In Ariel Rosenfeld and Nimrod Talmon, editors, Multi-Agent Systems - 18th European Conference, EUMAS 2021, Virtual Event, June 28-29, 2021, Revised Selected Papers, volume 12802 of Lecture Notes in Computer Science, pages 211–227. Springer, 2021a. ISBN 978-3-030-82253-8. doi: 10.1007/978-3-030-82254-5\_13. URL https://doi.org/10.1007/978-3-030-82254-5\_13.
  39. Modelling accuracy and trustworthiness of explaining agents. In Sujata Ghosh and Thomas Icard, editors, Logic, Rationality, and Interaction - 8th International Workshop, LORI 2021, Xi’ian, China, October 16-18, 2021, Proceedings, volume 13039 of Lecture Notes in Computer Science, pages 232–245. Springer, 2021b. ISBN 978-3-030-88707-0. doi: 10.1007/978-3-030-88708-7\_19. URL https://doi.org/10.1007/978-3-030-88708-7\_19.
  40. A review of formal methods applied to machine learning, 2021.
  41. Jonathan H. Warrell. A probabilistic dependent type system based on non-deterministic beta reduction. CoRR, abs/1602.06420, 2016. URL http://arxiv.org/abs/1602.06420.
  42. Jeannette M. Wing. Trustworthy ai. Commun. ACM, 64(10):64–71, sep 2021. ISSN 0001-0782. doi: 10.1145/3448248. URL https://doi.org/10.1145/3448248.
Citations (6)
View on Semantic Scholar

Summary

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

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

Tweets