Study finds exploits in ChatGPT, hackers can read all your conversations

Other AI-based chatbots had similar vulnerabilities, except Google Gemini

4 min. read

Published onMarch 18, 2024

published onMarch 18, 2024

Share this article

Read our disclosure page to find out how can you help Windows Report sustain the editorial teamRead more

If you share personal matters with ChatGPT or ask questions where private information is disclosed, stop that right away. A recent study suggests that chatbots, including ChatGPT, could be hacked, and all your conversations/chats may be accessible to attackers!

In the study conducted at Israel’sBen-Gurion University, researchers have found aside channelexploit present in almost every popular AI-based chatbot, except Google Gemini, that could reveal the entire conversation with high accuracy, though not100%.

In an email toArs Technica,Yisroel Mirsky, head of theOffensive AI Research Labat theBen-Gurion University,said,

Researchers shed light on the vulnerabilities in AI-based chatbots

The study is complex and slightly tricky for a regular user to comprehend. In simple terms, researchers exploited the side channel vulnerability to acquire tokens (data that helps LLMs translate user inputs) and then used them to infer the conversation with a55%accuracy.

Researchers leveraged the side channel attack technique because, with it, instead of directly attacking the system, they could gather the information it shared inadvertently. This way, they could bypass the built-in protection protocols, including encryption.

These tokens were then run through two specially trained LLMs (Large Language Models), which could translate the contents into text format. This is practically impossible if you take a manual approach.

However, since chatbots have a distinct style, researchers were able to train LLMs to effectively decipher the prompts. One LLM was trained to identify the first sentence of the response, while the other worked on inner sentences based on the context.

In the email toArs Technica, they explain it as,

This breakthrough is also mentioned in their research paper.

The researchers have shared a demo video of the entire process, fromTraffic InterceptiontoResponse Inference, onYouTube.

So, your ChatGPT chat isn’t as safe as you thought, and hackers may easily read it! Even though theside channelexploit wasn’t present in Google’s chatbot,researchers have hacked into Gemini AI and Cloud Consolepreviously.

Besides, there has been asignificant rise in cyberattacksafter AI became mainstream. A recent report by Microsoft suggests that in the UK,87% of companies stand the risk of facing AI-powered cyber attacks.

Microsoft’s President,Brad Smith, had his share ofconcerns regarding AIand called for immediate regulations!

What do you think about the rise of AI? Share with our readers in the comments section.

With KB5043178 to Release Preview Channel, Microsoft advises Windows 11 users to plug in when the battery is low#

Copilot in Outlook will generate personalized themes for you to customize the app#

Microsoft will raise the price of its 365 Suite to include AI capabilities#

Death Stranding Director’s Cut is now Xbox X|S at a huge discount#

Outlook will let users create custom account icons so they can tell their accounts apart easier#

Study finds exploits in ChatGPT, hackers can read all your conversations#

Researchers shed light on the vulnerabilities in AI-based chatbots#

With KB5043178 to Release Preview Channel, Microsoft advises Windows 11 users to plug in when the battery is low

Copilot in Outlook will generate personalized themes for you to customize the app

Microsoft will raise the price of its 365 Suite to include AI capabilities

Death Stranding Director’s Cut is now Xbox X|S at a huge discount

Outlook will let users create custom account icons so they can tell their accounts apart easier

Study finds exploits in ChatGPT, hackers can read all your conversations

Researchers shed light on the vulnerabilities in AI-based chatbots