# Black-Box Access is Insufficient for Rigorous AI Audits

**Type:** Papers  
**Canonical URL:** https://scholariq.org/papers/black-box-access-is-insufficient-for-rigorous-ai-audits/

## Facts

| Field | Value |
| --- | --- |
| Author Names | Stephen Casper,Carson Ezell,Charlotte Siegmann,Noam Kolt,Taylor Lynn Curtis,Ben Bucknall,Andreas Haupt,Kevin Wei,Jérémy Scheurer,Marius Hobbhahn,Lee Sharkey,Satyapriya Krishna,Marvin Von Hagen,Silas Alberti,Alan Chan,Qinyi Sun,Michael Gerovitch,David Bau,Max Tegmark,David Krueger,Dylan Hadfield-Menell |
| Citations | 64 |
| DOI | 10.1145/3630106.3659037 |
| Fields | Computer Science |
| Open Access | true |
| OA Status | gold |
| OA URL | https://dl.acm.org/doi/pdf/10.1145/3630106.3659037 |
| OpenAlex ID | https://openalex.org/W4391334942 |
| Type | conference-paper |
| Year | 2024 |

## Paper authors

- [Kevin Wei](https://scholariq.org/researchers/kevin-wei/)

## Paper primary topic

- [Adversarial Robustness in Machine Learning](https://scholariq.org/topics/adversarial-robustness-in-machine-learning/)

## Paper topics

- [Adversarial Robustness in Machine Learning](https://scholariq.org/topics/adversarial-robustness-in-machine-learning/)
- [Security and Verification in Computing](https://scholariq.org/topics/security-and-verification-in-computing/)
- [Information and Cyber Security](https://scholariq.org/topics/information-and-cyber-security/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.