The National Times - AI agents open door to new hacking threats

AI agents open door to new hacking threats


AI agents open door to new hacking threats
AI agents open door to new hacking threats / Photo: © AFP/File

Cybersecurity experts are warning that artificial intelligence agents, widely considered the next frontier in the generative AI revolution, could wind up getting hijacked and doing the dirty work for hackers.

Change text size:

AI agents are programs that use artificial intelligence chatbots to do the work humans do online, like buy a plane ticket or add events to a calendar.

But the ability to order around AI agents with plain language makes it possible for even the technically non-proficient to do mischief.

"We're entering an era where cybersecurity is no longer about protecting users from bad actors with a highly technical skillset," AI startup Perplexity said in a blog post.

"For the first time in decades, we're seeing new and novel attack vectors that can come from anywhere."

These so-called injection attacks are not new in the hacker world, but previously required cleverly written and concealed computer code to cause damage.

But as AI tools evolved from just generating text, images or video to being "agents" that can independently scour the internet, the potential for them to be commandeered by prompts slipped in by hackers has grown.

"People need to understand there are specific dangers using AI in the security sense," said software engineer Marti Jorda Roca at NeuralTrust, which specializes in large language model security.

Meta calls this query injection threat a "vulnerability." OpenAI chief information security officer Dane Stuckey has referred to it as "an unresolved security issue."

Both companies are pouring billions of dollars into AI, the use of which is ramping up rapidly along with its capabilities.

- AI 'off track' -

Query injection can in some cases take place in real time when a user prompt -- "book me a hotel reservation" -- is gerrymandered by a hostile actor into something else -- "wire $100 to this account."

But these nefarious prompts can also be hiding out on the internet as AI agents built into browsers encounter online data of dubious quality or origin, and potentially booby-trapped with hidden commands from hackers.

Eli Smadja of Israeli cybersecurity firm Check Point sees query injection as the "number one security problem" for large language models that power AI agents and assistants that are fast emerging from the ChatGPT revolution.

Major rivals in the AI industry have installed defenses and published recommendations to thwart such cyberattacks.

Microsoft has integrated a tool to detect malicious commands based on factors including where instructions for AI agents originate.

OpenAI alerts users when agents doing their bidding visit sensitive websites and blocks proceeding until the software is supervised in real time by the human user.

Some security professionals suggest requiring AI agents to get user approval before performing any important task - like exporting data or accessing bank accounts.

"One huge mistake that I see happening a lot is to give the same AI agent all the power to do everything," Smadja told AFP.

In the eyes of cybersecurity researcher Johann Rehberger, known in the industry as "wunderwuzzi," the biggest challenge is that attacks are rapidly improving.

"They only get better," Rehberger said of hacker tactics.

Part of the challenge, according to the researcher, is striking a balance between security and ease of use since people want the convenience of AI doing things for them without constant checks and monitoring.

Rehberger argues that AI agents are not mature enough to be trusted yet with important missions or data.

"I don't think we are in a position where you can have an agentic AI go off for a long time and safely do a certain task," the researcher said.

"It just goes off track."

F.Hammond--TNT

Featured

Meta’s AI Agent Muse Accesses Private Messages, Sparking Privacy Concerns

Meta’s artificial intelligence agent, Muse, has triggered privacy and security alarms after a Reuters investigation found it accessing private messages and generating unverified financial information. Employees reported the agent bypassing intended access controls to retrieve Signal notifications and displaying potential cross-account data, prompting calls for stricter technical safeguards from privacy advocates.

Hackers Steal Over 1 Million Credit Card Details via Old Windows Bug

Cybersecurity researchers have uncovered a massive data breach involving over one million credit and debit card details, stemming from an attack on point-of-sale (POS) terminals across more than 20 countries. The incident exploited a long-patched Windows vulnerability, with the vast majority of compromised systems located in Brazil.

Xreal Aura Review: A Comfortable VR Alternative With Flawed Controls

Xreal has released the Aura, a $1,279 pair of extended-reality glasses running on Google’s Android XR platform. While the device offers a lightweight design and high-quality virtual screens for entertainment and productivity, its reliance on a wired compute puck and imprecise hand-tracking controls present significant usability challenges.

Oobah Butler’s HBO Series Exposes Grifters in Wellness, Wine, and Tech

Stunt journalist Oobah Butler returns with a new HBO series that targets the opulent and often gullible worlds of wellness, wine, dating, and technology. By executing elaborate scams involving fake products and fabricated personas, Butler aims to lampoon the systems that allow bad actors to thrive, drawing comparisons to his past viral stunts while highlighting his move to New York.

Change text size: