Josh has worked a freelance writer for the past ten years, writing news and features focusing on the gaming, science, and tech industries. He has covered big events like E3, CES, and a slew of other smaller press events oriented around the latest consumer technology and gadgets.
While some popular browsers have opted to gradually plug in AI features over time — like Google Chrome with Gemini — others, like Perplexity's Comet browser and, are built from the ground up to utilize AI functions, including AI agents.
. Now, whether you're riding the AI wave or not, there's one thing that's hard to ignore, and that's the number of security risks that using browsers with AI agents has introduced., they can also be extremely helpful at giving users the ability to approach web browsing from a different direction. However, one major security risk has stood out above the rest: the fact that AI agents like those used in browsers like Atlas and Comet can be thwarted and overridden with the use of prompt injections. That can allow bad actors to take control of an AI agent or intercept information and data, and the user might not ever know it happened.agents. And, if picked up by other browsers, perhaps the system could make AI agents and AI browsers more feasible and safe to use in the long run.According to Perplexity's post about the new system, it's designed around a special"defense architecture" that builds off benchmarks and a new detection model. These components are meant to come together in a way that not only secures AI agents, but secures them specifically for the"open-world web environment." To be frank, these improvements could not have come at a better time — aside from when the models were first released — as new methods with which to break and exploit AI products and services pop up every week. Not only have researchers repeatedly proven that they can take control of different systems using AI — they onceIn order to make BrowseSafe a viable security system, Perplexity put together a ton of research on all of the known attack vectors. They used that information to help create a benchmark, which was paramount in training a real world detection model. This model has to run asynchronously alongside AI agents, and Perplexity says it has fine-tuned the model to do just that. Of course, whether or not this new system will be widely adopted is another conversation entirely. There's also the question of just how long it will take bad actors to come up with ways to circumvent the system, as security researchers are constantly finding new threats out in the wild.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Kremlin praises new U.S. security strategy as Russian strikes kill 4 in UkraineThe new policy says that the U.S. hopes to 'reestablish strategic stability with Russia.'
Read more »
New York and New Jersey are awful places to be single, according to new surveyNew York City was rated toward the bottom of all cities in the U.S. for singles, according to a survey by personal finance website WalletHub that ranked cities…
Read more »
Kremlin Says New U.S. Security Strategy Accords Largely With Russia's View“The adjustments that we see correspond in many ways to our vision,” a Kremlin spokesman said.
Read more »
Local Mayors alert residents to security breach in Emergency Notification SystemOnSolve CodeRED, a nationwide emergency alert platform, has been victim of a data breach leaving subscribers vulnerable, and urges those subscribers to take precautionary steps.
Read more »
New San Diego border chief talks security, enforcementMelissa Mecija joined the 10News team in July 2010. She currently works as a 10News This Morning weekday anchor.
Read more »
The Best Way to View Trump’s Alarming New National Security StrategyIt’s an unserious document—but it can tell us a few things about how Trump sees the world.
Read more »