Trustworthy AI

The promise of AI is huge. AI systems have already achieved good enough performance to be in our streets and in our homes. However, they can be brittle and unfair. For society to reap the benefits of AI systems, society needs to be able to trust them. Inspired by decades of progress in trustworthy computing, we suggest what trustworthy properties would be desired of AI systems. By enumerating a set of new research questions, we explore one approach--formal verification--for ensuring trust in AI. Trustworthy AI ups the ante on both trustworthy computing and formal methods.

[1]  Sanjit A. Seshia,et al.  VerifAI: A Toolkit for the Formal Design and Analysis of Artificial Intelligence-Based Systems , 2019, CAV.

[2]  Insup Lee,et al.  Case study: verifying the safety of an autonomous racing car with a neural network controller , 2019, HSCC.

[3]  Yuriy Brun,et al.  Preventing undesirable behavior of intelligent machines , 2019, Science.

[4]  Adam Chlipala,et al.  Verifying a high-performance crash-safe file system using a tree specification , 2017, SOSP.

[5]  Michael M. Zavlanos,et al.  Reduced variance deep reinforcement learning with temporal logic specifications , 2019, ICCPS.

[6]  Alexandra Chouldechova,et al.  Fair prediction with disparate impact: A study of bias in recidivism prediction instruments , 2016, Big Data.

[7]  Michel Dubois,et al.  Verification techniques for cache coherence protocols , 1997, CSUR.

[8]  Joseph Sifakis,et al.  Specification and verification of concurrent systems in CESAR , 1982, Symposium on Programming.

[9]  Thomas A. Henzinger,et al.  Automatic Symbolic Verification of Embedded Systems , 1996, IEEE Trans. Software Eng..

[10]  Benjamin C. Pierce,et al.  From C to interaction trees: specifying, verifying, and testing a networked server , 2018, CPP.

[11]  C. Newcombe,et al.  How Amazon web services uses formal methods , 2015, Commun. ACM.

[12]  W. Hager,et al.  and s , 2019, Shallow Water Hydraulics.

[13]  Edmund M. Clarke,et al.  Characterizing Correctness Properties of Parallel Programs Using Fixpoints , 1980, ICALP.

[14]  Gerhard Goos,et al.  Theory of Cryptography , 2010, Lecture Notes in Computer Science.

[15]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[16]  A. Murawski.  Foundations and Trends R © in Programming Languages , 2016 .

[17]  Sanjit A. Seshia,et al.  Formal Specification for Deep Neural Networks , 2018, ATVA.

[18]  Nikhil Swamy,et al.  Everest: Towards a Verified, Drop-in Replacement of HTTPS , 2017, SNAPL.

[19]  F. Schneider.  Trust in Cyberspace , 1998 .

[20]  John Harrison.  Formal verification at Intel , 2003, 18th Annual IEEE Symposium of Logic in Computer Science, 2003. Proceedings..

[21]  P Tiwari,et al.  Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study , 2016, American Journal of Neuroradiology.

[22]  Jiqiang Guo,et al.  Stan: A Probabilistic Programming Language. , 2017, Journal of statistical software.

[23]  Andrew L. Beam,et al.  Adversarial attacks on medical machine learning , 2019, Science.

[24]  Carleen Maitland,et al.  Trust in cyberspace , 2000 .

[25]  Toniann Pitassi,et al.  Fairness through awareness , 2011, ITCS '12.

[26]  Adam Chlipala,et al.  Using Crash Hoare logic for certifying the FSCQ file system , 2015, USENIX Annual Technical Conference.