AI safety & securitymedium
Critical Flaws in Ollama AI Framework Could Enable DoS, Model Theft, and Poisoning
Vulnerabilities mentioned
All| CVE | Vulnerability | CVSS | EPSS | Signals | Published |
|---|---|---|---|---|---|
| CVE-2024-37032 | Ollama before 0.1.34 does not validate the format of the digest (sha256 with 64 hex digits) when getting the model path, and thus mishandles the… | 8.8 | 90% | PoC | |
CVE-2024-39720+3 related CVEs | An issue was discovered in Ollama before 0.1.46 | 8.2 group max | 2% | PoC |
From the original article
2 min read at thehackernews.com
Ravie Lakshmanan Nov 04, 2024 Vulnerability / Cyber Threat Cybersecurity researchers have disclosed six security flaws in the Ollama artificial intelligence (AI) framework that could be exploited by a malicious actor to perform various actions, including denial-of-service, model poisoning, and model theft.
By @TheHackersNews · thehackernews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.