Sunday, November 17, 2024

Cyber AI

Promptmap – Tool to Test Prompt Injection Attacks on ChatGPT Instances

Prompt injection refers to a technique where users input specific prompts or instructions to influence the responses generated by a language model like ChatGPT.However,...

Researchers Uncovered a New Flaw in ChatGPT to Turn Them Evil

LLMs are commonly trained on vast internet text data, often containing offensive content. To mitigate this, developers use "alignment" methods via finetuning to prevent...

FraudGPT: A New Dark Side AI Tool For Cyber Criminals

A new tool called FraudGPT has been launched by cybercriminals which pose a serious threat to both individuals and businesses.This black-hat-based tool is...

Google Outlines Common Red Team Attacks Targeting AI Systems

There are rising concerns about the security risks associated with artificial intelligence (AI), which is becoming more and more popular and pervasive.Google, a major...

WormGPT: Cybercriminals AI Tool Gained Over 5,000 Subscribers in Just a Week

The revolutionary innovations by AI (Artificial Intelligence) include generative AI that has various creative potential, but along with that it also raises serious concerns...

Poisoned Facebook Ads Deliver Malware Using Fake ChatGPT, Bard & Other AI Services

Cyber criminals have recently started using Facebook to pretend to be well-known generative AI brands like ChatGPT, Google Bard, Midjourney, and Jasper to steal users'...

WormGPT – A ChatGPT Themed Hacking Tool Used to Launch Cyber Attack

WormGPT, a black-hat-based tool has been recently launched by cybercriminals and has the potential to conduct various social engineering as well as Business Email...

ChatGPT Reconnaissance Techniques for Penetration Testing Success

ChatGPT is one of the biggest and most sophisticated language models ever made, with a massive neural network of over 175 billion parameters.Recent research...