Pierluigi Paganini March 14, 2024
Researchers found multiple flaws in ChatGPT plugins

Researchers analyzed ChatGPT plugins and discovered several types of vulnerabilities that could lead to data exposure and account takeover. Researchers from Salt Security discovered three types of vulnerabilities in ChatGPT plugins that can be could have led to data exposure and account takeovers. ChatGPT plugins are additional tools or extensions that can be integrated with […]

Pierluigi Paganini February 15, 2024
Nation-state actors are using AI services and LLMs for cyberattacks

Microsoft and OpenAI warn that nation-state actors are using ChatGPT to automate some phases of their attack chains, including target reconnaissance and social engineering attacks. Multiple nation-state actors are exploiting artificial intelligence (AI) and large language models (LLMs), including OpenAI ChatGPT, to automate their attacks and increase their sophistication. According to a study conducted by […]

Pierluigi Paganini January 30, 2024
Italian data protection authority said that ChatGPT violated EU privacy laws

Italian data protection authority regulator authority Garante said that ChatGPT violated European Union data privacy regulations. The Italian data protection authority regulator authority, known as “Garante per la protezione dei dati personali”, announced it has notified OpenAI that ChatGPT violated the EU data protection regulation GDPR. In early April 2023, the Italian Data Protection Authority temporarily […]

Pierluigi Paganini December 02, 2023
Researchers devised an attack technique to extract ChatGPT training data

Researchers devised an attack technique that could have been used to trick ChatGPT into disclosing training data. A team of researchers from several universities and Google have demonstrated an attack technique against ChetGPT that allowed them to extract several megabytes of ChatGPT’s training data. The researchers were able to query the model at a cost […]

Pierluigi Paganini November 17, 2023
The board of directors of OpenAI fired Sam Altman

OpenAI fired its CEO Sam Altman, and the Chief technology officer Mira Murati appointed interim CEO to lead the company. Sam Altman has been removed as CEO of OpenAI. The company announced that Mira Murati, the Chief Technology Officer, has been appointed as interim CEO. He was distrusted by the board for his behavior, for […]

Pierluigi Paganini November 09, 2023
DDoS attack leads to significant disruption in ChatGPT services

OpenAI confirmed that the outage suffered by ChatGPT and its API on Wednesday was caused by a distributed denial-of-service (DDoS) attack. OpenAI confirmed earlier today that the outage suffered by ChatGPT and its API on Wednesday was caused by a distributed denial-of-service (DDoS) attack. “We are dealing with periodic outages due to an abnormal traffic pattern […]

Pierluigi Paganini July 26, 2023
FraudGPT, a new malicious generative AI tool appears in the threat landscape

FraudGPT is another cybercrime generative artificial intelligence (AI) tool that is advertised in the hacking underground. Generative AI models are becoming attractive for crooks, Netenrich researchers recently spotted a new platform dubbed FraudGPT which is advertised on multiple marketplaces and the Telegram Channel since July 22, 2023.  According to Netenrich, this generative AI bot was […]

Pierluigi Paganini July 16, 2023
WormGPT, the generative AI tool to launch sophisticated BEC attacks

The WormGPT case: How Generative artificial intelligence (AI) can improve the capabilities of cybercriminals and allows them to launch sophisticated attacks. Researchers from SlashNext warn of the dangers related to a new generative AI cybercrime tool dubbed WormGPT. Since chatbots like ChatGPT made the headlines, cybersecurity experts warned of potential abuses of Generative artificial intelligence (AI) […]

Pierluigi Paganini May 22, 2023
BatLoader campaign impersonates ChatGPT and Midjourney to deliver Redline Stealer

Researchers identified an ongoing BatLoader campaign relying on Google Search Ads to deliver rogue web pages for ChatGPT and Midjourney. In early May, researchers at eSentire Threat Response Unit (TRU) spotted an ongoing BatLoader campaign using Google Search Ads to redirect victims to imposter web pages for AI-based services like ChatGPT and Midjourney. The rogue […]

Pierluigi Paganini April 28, 2023
OpenAI reinstates ChatGPT service in Italy after meeting Garante Privacy’s demands

OpenAI announced that access to its chatbot service ChatGPT is allowed again in Italy after the company met the demands of regulators. OpenAI restored access to ChatGPT in Italy after the company met the demands of the Italian Data Protection Authority, Garante Privacy. In early April, the Italian Data Protection Authority temporarily banned ChatGPT due […]