AI Browser is not free from danger: This way you can breach your privacy, your data can reach hackers...

Artificial Intelligence (AI) is changing the way we use the internet. Recently, several AI browsers have launched, transforming the way we search. AI browsers have built-in assistants that simplify your searching, browsing, and online activities. OpenAI's ChatGPT Atlas and Perplexity's Comet are two such browsers that claim to offer a fast and interactive online experience. Other browsers, such as Opera Neon and Dia, are also experimenting in this direction. But the question arises: are these AI browsers truly secure?

Privacy Threats Looming
Recently, security researchers at the privacy-focused browser Brave issued a serious warning about these browsers. They found that Comet and some other AI browsers could allow hackers to access personal information and launch cyberattacks using "Indirect Prompt Injection."

Under this technique, hackers hide invisible text in websites or images. When an AI browser scans the page or image, it discovers the hidden command and unknowingly begins to follow the hacker's instructions. This can pose a significant threat to user privacy and device security.

What is Prompt Injection?
Recently, researchers at Brave demonstrated Prompt Injection on the Perplexity Comet. They hid light blue text against a yellow background, making it nearly impossible to see with the naked eye. Surprisingly, the AI could easily read this text. As soon as the AI read the text, it interpreted the hacker's command as a user command and took action. This gave the hacker unauthorized access to user information.

OpenAI's Browser Also Vulnerable
OpenAI also acknowledged, while launching ChatGPT Atlas, that such browsers introduce new risks. The company did state that Atlas doesn't access other data on your system, but it didn't explain how it protects against such "prompt injections." Many users have claimed on social media that even Atlas isn't completely immune to this threat.

AI Browsers Increasing Risks
The growing capabilities of AI browsers are encouraging, but ignoring security can be costly. Developers now need to develop robust safeguards to prevent AI tools from being misused. For now, users should exercise caution, avoid suspicious websites, and monitor their browser activity. Convenience should never come at the expense of security.

Disclaimer: This content has been sourced and edited from News 18 hindi. While we have made modifications for clarity and presentation, the original content belongs to its respective authors and website. We do not claim ownership of the content.