Assessing the security posture of a widely used vision model: YOLOv7
blog.trailofbits.com | vulnerability | #rce | #open-source | #denial-of-service | #deserialization | #vulnerability | #machine-learning | #computer-vision | #trail-of-bits | #model-security | #yolov7
Summary
Trail of Bits found 11 vulnerabilities in YOLOv7, including YAML parsing that enables remote code execution, denial of service, and model differentials, deeming it unfit for mission-critical use.
- Published
- Collected
--- id: 1602 title: "Assessing the security posture of a widely used vision model: YOLOv7" source_domain: blog.trailofbits.com source_url: "https://blog.trailofbits.com/2023/11/15/assessing-the-security-posture-of-a-widely-used-vision-model-yolov7/" published_at: "2023-11-15T15:15:05Z" tags: ["rce", "open-source", "denial-of-service", "deserialization", "vulnerability", "machine-learning", "computer-vision", "trail-of-bits", "model-security", "yolov7"] phying_url: "https://phying.com/item/1602" lang: en --- # Assessing the security posture of a widely used vision model: YOLOv7 ## Summary Trail of Bits found 11 vulnerabilities in YOLOv7, including YAML parsing that enables remote code execution, denial of service, and model differentials, deeming it unfit for mission-critical use. ## Intelligence Metadata - **Sources:** blog.trailofbits.com - **Published:** 2023-11-15T15:15:05Z - **Original:** https://blog.trailofbits.com/2023/11/15/assessing-the-security-posture-of-a-widely-used-vision-model-yolov7/ - **Phying News:** https://phying.com/item/1602