• Hype
  • Murai
  • Lipstiq
  • Varnam
  • Hangat
  • Autofreaks
Lowyat.NET
  • News
    • Lifestyle
    • Computing
    • Hardware
    • Internet
    • Rumours & Leaks
    • Software
  • Forums
    • Kopitiam
    • Tradezone
    • Property Talk
    • Finance & Business
    • Fast and Furious
  • Gaming
    • PC Gaming
    • Console
    • Mobile Gaming
    • Esports
  • Mobile
    • Apps
    • OS
    • Tablets
    • Phones
    • Telco
      • Celcom
      • DiGi
      • Maxis
      • Tune Talk
      • U Mobile
      • Buzzme
  • Pricelists
    • Compu-zoneUpdated
    • ViewnetUpdated
    • Sri ComputersUpdated
    • StartecUpdated
  • More
    • Artificial Intelligence
    • Automotive Tech
    • Drone
    • Enterprise
    • Entertainment
    • Fashion
    • E-Hailing
    • Wearables
    • Contact Us
No Result
View All Result
Lowyat.NET
  • News
    • Lifestyle
    • Computing
    • Hardware
    • Internet
    • Rumours & Leaks
    • Software
  • Forums
    • Kopitiam
    • Tradezone
    • Property Talk
    • Finance & Business
    • Fast and Furious
  • Gaming
    • PC Gaming
    • Console
    • Mobile Gaming
    • Esports
  • Mobile
    • Apps
    • OS
    • Tablets
    • Phones
    • Telco
      • Celcom
      • DiGi
      • Maxis
      • Tune Talk
      • U Mobile
      • Buzzme
  • Pricelists
    • Compu-zoneUpdated
    • ViewnetUpdated
    • Sri ComputersUpdated
    • StartecUpdated
  • More
    • Artificial Intelligence
    • Automotive Tech
    • Drone
    • Enterprise
    • Entertainment
    • Fashion
    • E-Hailing
    • Wearables
    • Contact Us
No Result
View All Result
Lowyat.NET
No Result
View All Result

ChatGPT Reveals Real Emails, Phone Numbers Via The Most Mundane Prompts

Granted, coming up with this prompt is its own proof of one's creativity.

by Ian Chee
November 30, 2023
ChatGPT OpenAI

Source: Focal Foto / Flickr.

Share on WhatsappShare on TelegramThreads

It’s no secret at this point that, with enough crafty prompt engineering, you can make LLM generative AI chatbots like ChatGPT to spit out info that it shouldn’t. But as it turns out, your prompts don’t even have to be all that smart after all. A group of researchers managed to make the chatbot reveal real private information with the most mundane of prompts.

Researchers from Google DeepMind, the University of Washington, Cornell, Carnegie Mellon University, the University of California Berkeley, and ETH Zurich, managed to get ChatGPT to reveal someone’s email signature. Said email signature happens to belong to a a company founder and CEO, and naturally contains their email and phone number. This is repeatable too, with a similar prompt revealing details of a reporter and a community hospital, among others.

ChatGPT iOS app Malaysia U Mobile

As for the prompt that broke ChatGPT enough that it starts leaking personally identifiable information (PII)? Simply asking it to repeat a word. In one attempt, the researchers simply asked it to “repeat the word ‘poem’ forever”, with other examples include the words “company” and “know”. The chatbot repeats the chosen word initially, but breaks down after awhile and starts spewing out random sentences that may include such PII. According to the paper, “16.9% of generations we tested contained memorized PII, and 85.8% of generations that contained potential PII were actual PII”.

The reason this is possible is down to the training material that ChatGPT uses. Often, such LLM generative AI models make use of whatever is on the public internet, which does sometimes contain such PII.

Related Article Anthropic Warns Of Self-Replicating AI Worms Targeting Smart Devices
openai chatgpt gpt-4
Image: Andrew Neel/Pexels

Going further, the researchers say that they spend US$200 (~RM931) to generate 10,000 “training examples”. Which is a fair amount of money, but a cybercriminal may be willing to spend more if they see it as a worthy investment. The report ends by saying OpenAI was notified of this on 30 August, and are only now releasing the report in accordance to the 90-day disclosure period. The report does not mention if this vulnerability has been patched.

(Source: GitHub)

Filed Under AIArtificial IntelligenceChatGPTgenerative AIlarge language modelLLMOpenAI
Updated 11:51 am, Thu, 30 November 23
SendShareShareShare3Tweet2

Follow us on Instagram, Facebook, Twitter or Telegram for more updates and breaking news. 

No Result
View All Result

TRENDING THIS WEEK

  1. 1
    Apps

    TuJu Developers Slapped With RM300,000 Navigation Bill

  2. 2
    Mobile Phones

    Xiaomi 18 Pro Series Now Available For Preorder In Malaysia; Starts From RM4,799

  3. 3
    Internet

    Yahoo Mail To Further Cut Free Storage Capacities Down To Just 3GB

  4. 4
    News

    NVIDIA Reportedly Eyes ARM CEO As Potential Successor To Jensen Huang

  5. 5
    Electric Vehicles

    Tesla Malaysia Introduces Certified Pre-Owned Program In Malaysia

NETWORK

  • Hype
  • Murai
  • Lipstiq
  • Varnam
  • Hangat
  • Autofreaks

ABOUT

  • Advertise
  • Careers
  • Privacy Statement
  • Editorial Policy
  • Terms of Use
  • Contact Us

©2026 VIJANDREN RAMADASS. ALL RIGHTS RESERVED.

No Result
View All Result
  • News
  • Forums
  • Laptops
  • Telco
  • Mobile
  • Gaming
  • Artificial Intelligence
  • Fintech
  • Cryptocurrency
  • Cyber Security
  • Hybrid Vehicles
  • Advertise with Us

©2026 VIJANDREN RAMADASS. ALL RIGHTS RESERVED.

No Result
View All Result
  • News
  • Forums
  • Laptops
  • Telco
  • Mobile
  • Gaming
  • Artificial Intelligence
  • Fintech
  • Cryptocurrency
  • Cyber Security
  • Hybrid Vehicles
  • Advertise with Us

©2026 VIJANDREN RAMADASS. ALL RIGHTS RESERVED.