US EditionOpenAI Hardens ChatGPT Atlas Against Prompt Injection Attacks
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.4 Articles
4 Articles
TechCrunch: OpenAI says AI browsers may always be vulnerable to prompt injection attacks | ResearchBuzz: Firehose
TechCrunch: OpenAI says AI browsers may always be vulnerable to prompt injection attacks. “Even as OpenAI works to harden its Atlas AI browser against cyberattacks, the company admits that prompt injections, a type of attack that manipulates AI agents to follow malicious instructions often hidden in web pages or emails, is a risk that’s not going away anytime soon — raising questions about how safely AI agents can operate on the open web.” The p…
eSecurityPlanet
IT Security News - cybersecurity, infosecurity newsOpenAI Hardens ChatGPT Atlas Against Prompt Injection Attacks
OpenAI has rolled out a security update for its browser-based ChatGPT Atlas agent to counter prompt injection attacks. The update introduces new model-level and system-level defenses designed to prevent malicious instructions hidden in web content from overriding user intent. An attacker “… could send a malicious email attempting to trick an agent to ignore the user’s request and instead forward sensitive tax documents to an attacker-controlled…
OpenAI enhances the security of Atlas, its IA browser. The company recognizes that quick injections, these attacks aimed at hijacking the agent, will remain a permanent problem, but relies on an automated system to discover them before hackers.
Coverage Details
Bias Distribution
- There is no tracked Bias information for the sources covering this story.
Factuality
To view factuality data please Upgrade to Premium
