TU Darmstadt / ULB / TUbiblio

Trustworthy AI Inference Systems: An Industry Research View

Cammarota, Rosario ; Schunter, Matthias ; Rajan, Anand ; Boemer, Fabian ; Kiss, Ágnes ; Treiber, Amos ; Weinert, Christian ; Schneider, Thomas ; Stapf, Emmanuel ; Sadeghi, Ahmad-Reza ; Demmler, Daniel ; Chen, Huili ; Hussain, Siam Umar ; Riazi, M. Sadegh ; Koushanfar, Farinaz ; Gupta, Saransh ; Rosing, Tajan Simunic ; Chaudhuri, Kamalika ; Nejatollahi, Hamid ; Dutt, Nikil ; Imani, Mohsen ; Laine, Kim ; Dubey, Anuj ; Aysu, Aydin ; Sadat Hosseini, Fateme ; Yang, Chengmo ; Wallace, Eric ; Norton, Pamela (2020)
Trustworthy AI Inference Systems: An Industry Research View.
doi: 10.48550/arXiv.2008.04449
Report, Bibliographie

Kurzbeschreibung (Abstract)

In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized inferences to aid their decision, while at the same time utilizing appropriate security protection mechanisms for AI models. Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time. To approach the subject, we start by introducing current trends in AI inference systems. We continue by elaborating on the relationship between Intellectual Property (IP) and private data protection in such systems. Regarding the protection mechanisms, we survey the security and privacy building blocks instrumental in designing, building, deploying, and operating private AI inference systems. For example, we highlight opportunities and challenges in AI systems using trusted execution environments combined with more recent advances in cryptographic techniques to protect data in use. Finally, we outline areas of further development that require the global collective attention of industry, academia, and government researchers to sustain the operation of trustworthy AI inference systems.

Typ des Eintrags: Report
Erschienen: 2020
Autor(en): Cammarota, Rosario ; Schunter, Matthias ; Rajan, Anand ; Boemer, Fabian ; Kiss, Ágnes ; Treiber, Amos ; Weinert, Christian ; Schneider, Thomas ; Stapf, Emmanuel ; Sadeghi, Ahmad-Reza ; Demmler, Daniel ; Chen, Huili ; Hussain, Siam Umar ; Riazi, M. Sadegh ; Koushanfar, Farinaz ; Gupta, Saransh ; Rosing, Tajan Simunic ; Chaudhuri, Kamalika ; Nejatollahi, Hamid ; Dutt, Nikil ; Imani, Mohsen ; Laine, Kim ; Dubey, Anuj ; Aysu, Aydin ; Sadat Hosseini, Fateme ; Yang, Chengmo ; Wallace, Eric ; Norton, Pamela
Art des Eintrags: Bibliographie
Titel: Trustworthy AI Inference Systems: An Industry Research View
Sprache: Englisch
Publikationsjahr: 10 August 2020
Verlag: arXiv
Reihe: Cryptography and Security
Auflage: 1. Version
DOI: 10.48550/arXiv.2008.04449
URL / URN: https://arxiv.org/abs/2008.04449
Kurzbeschreibung (Abstract):

In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized inferences to aid their decision, while at the same time utilizing appropriate security protection mechanisms for AI models. Additionally, such systems should also use Privacy-Enhancing Technologies (PETs) to protect customers' data at any time. To approach the subject, we start by introducing current trends in AI inference systems. We continue by elaborating on the relationship between Intellectual Property (IP) and private data protection in such systems. Regarding the protection mechanisms, we survey the security and privacy building blocks instrumental in designing, building, deploying, and operating private AI inference systems. For example, we highlight opportunities and challenges in AI systems using trusted execution environments combined with more recent advances in cryptographic techniques to protect data in use. Finally, we outline areas of further development that require the global collective attention of industry, academia, and government researchers to sustain the operation of trustworthy AI inference systems.

Freie Schlagworte: Primitives, P3, Solutions, S2, Engineering, E4
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Praktische Kryptographie und Privatheit
20 Fachbereich Informatik > Systemsicherheit
DFG-Sonderforschungsbereiche (inkl. Transregio)
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Graduiertenkolleg 2050 Privacy and Trust for Mobile Users
Profilbereiche
Profilbereiche > Cybersicherheit (CYSEC)
LOEWE
LOEWE > LOEWE-Zentren
LOEWE > LOEWE-Zentren > CRISP - Center for Research in Security and Privacy
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1119: CROSSING – Kryptographiebasierte Sicherheitslösungen als Grundlage für Vertrauen in heutigen und zukünftigen IT-Systemen
Hinterlegungsdatum: 25 Aug 2020 07:57
Letzte Änderung: 06 Aug 2024 09:13
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen