Tesla Autopilot’s Lane Recognition Allegedly Vulnerable to Adversarial Attacks

March 29, 2019

Research by Tencent Keen Security Lab uncovered potential vulnerabilities in Tesla’s Autopilot system, including crafted adversarial samples and remote controlling via wireless gamepad. However, Tesla disputes their practical applicability in real-world scenarios. This incident raises awareness for responsible AI governance and the need for trustworthy AI practices. For those interested in shaping safe and secure autonomous driving, JOIN US to Govern and Map these crucial findings.

This incident has been downgraded to an issue as it does not meet current ingestion criteria.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

MEASURE 2.6 — similarity 0.687, rank 1. TAIM detail and related incidents →
MAP 1.6 — similarity 0.683, rank 2. TAIM detail and related incidents →
MEASURE 2.10 — similarity 0.672, rank 3. TAIM detail and related incidents →

Alleged deployer: tesla
Alleged developer: tesla
Alleged harmed parties: tesla-drivers

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/159

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.