Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909268665434112 |
|---|---|
| author | Cattell, Sven Ghosh, Avijit Kaffee, Lucie-Aimée |
| author_facet | Cattell, Sven Ghosh, Avijit Kaffee, Lucie-Aimée |
| contents | Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated Vulnerability Disclosure (CVD) ecosystem in software security. While global efforts to establish frameworks for AI transparency and collaboration are underway, the unique challenges presented by machine learning (ML) models demand a specialized approach. To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues. This paper reviews the evolution of ML disclosure practices, from ad hoc reporting to emerging participatory auditing methods, and compares them with cybersecurity norms. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We also outline a forthcoming real-world pilot of CFD. We argue that CFD could significantly enhance public trust in AI systems. By balancing organizational and community interests, CFD aims to improve AI accountability in a rapidly evolving technological landscape. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_07039 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities Cattell, Sven Ghosh, Avijit Kaffee, Lucie-Aimée Artificial Intelligence Cryptography and Security Computers and Society Harm reporting in Artificial Intelligence (AI) currently lacks a structured process for disclosing and addressing algorithmic flaws, relying largely on an ad-hoc approach. This contrasts sharply with the well-established Coordinated Vulnerability Disclosure (CVD) ecosystem in software security. While global efforts to establish frameworks for AI transparency and collaboration are underway, the unique challenges presented by machine learning (ML) models demand a specialized approach. To address this gap, we propose implementing a Coordinated Flaw Disclosure (CFD) framework tailored to the complexities of ML and AI issues. This paper reviews the evolution of ML disclosure practices, from ad hoc reporting to emerging participatory auditing methods, and compares them with cybersecurity norms. Our framework introduces innovations such as extended model cards, dynamic scope expansion, an independent adjudication panel, and an automated verification process. We also outline a forthcoming real-world pilot of CFD. We argue that CFD could significantly enhance public trust in AI systems. By balancing organizational and community interests, CFD aims to improve AI accountability in a rapidly evolving technological landscape. |
| title | Coordinated Flaw Disclosure for AI: Beyond Security Vulnerabilities |
| topic | Artificial Intelligence Cryptography and Security Computers and Society |
| url | https://arxiv.org/abs/2402.07039 |