After Spending Billions, OpenAI Still Has Gaps in Its Cybersecurity
10 Articles
10 Articles
CSO Online
cybernoz.comAfter spending billions, OpenAI still has gaps in its cybersecurity
Two separate reports of security flaws in OpenAI systems highlight how even a company spending billions on developing its own AI-powered cybersecurity testing tools remains vulnerable. In one incident, researchers breached OpenAI systems with the help of a rival AI developer’s tools, while another group of researchers tricked OpenAI’s Codex agent into bypassing its sandbox controls. Researchers from Hacktron chained multiple vulnerabilities to a…
Cybersecurity tests conducted by AI development company OpenAI to measure the capabilities of AI models have shown that AI agents have pushed their own boundaries and organized themselves... Click here for more.
Three Hacktron AI researchers reached OpenAI's internal code repository in July without touching a single model. Their path left the editor's help forum, a Speech instance, by a flaw in the libheif image library. A default configuration of OpenAI's single authentication then opened the employee accounts [...]
Malicious HEIF Upload Reached OpenAI’s Internal GitHub, Researchers Reveal
Researchers have disclosed how a malicious HEIF image uploaded to OpenAI’s public community forum ultimately opened a path to the company’s internal GitHub environment. Hacktron published the full attack chain on September 13, detailing a July 25 compromise of OpenAI’s Discourse-hosted forum that researchers chained with a separate single sign-on flaw. The group gained access to employee ChatGPT and Codex accounts and used one GitHub-connected C…
The security of OpenAI Codex entered the radar of researchers after the discovery of two vulnerabilities capable of breaking the isolation used by the programming agent. Battified from Heapjack and Overpatch, the failures were found by the Accomplish AI team and demonstrated that a malicious project could explore components of Codex to overcome the barriers of sandbox. The problem deserves attention because artificial intelligence-based programm…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
