Skip to main content
zenodoopen

Replication Package: How Artificial-Intelligence Incidents Can Jeopardize Safety and Security

<p><strong>Welcome to the public repository for the additional content of the paper "SoK: How Artificial-Intelligence Incidents Can Jeopardize Safety and Security", accepted at the ARES 2024.</strong></p> <p>This repository provides additional information to the conducted study, including the following file:</p> <ul> <li>analysis_sheet_ARES2024.csv: sheet containing security- and safety-related data regarding the harmonized datasets AIAAIC, AIID, AVID and Where In the World Is AI?, including 240 incidents classified according to the extraction criteria given in the paper.</li> </ul>

ShareScore

36/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
20
Reuse readiness
8
Engagement
0