Pierluigi Paganini
October 09, 2024
Resecurity reports a rise in attacks on AI Conversational platforms, targeting chatbots that use NLP and ML to enable automated, human-like interactions with consumers. Resecurity has observed a spike in malicious campaigns targeting AI agents and Conversational AI platforms that leverage chatbots to provide automated, human-like interactions for consumers. Conversational AI platforms are designed to […]
Pierluigi Paganini
September 16, 2024
A hacker tricked ChatGPT into providing instructions to make homemade bombs demonstrating how to bypass the chatbot safety guidelines. A hacker and artist, who goes online as Amadon, tricked ChatGPT into providing instructions to make homemade bombs bypassing the safety guidelines implemented by the chatbot. Initially, the expert asked for detailed instructions to create a […]
Pierluigi Paganini
July 18, 2024
AI systems are transforming technology and driving innovation across industries. How to protect privacy and build secure AI products? How to Protect Privacy and Build Secure AI Products AI systems are transforming technology and driving innovation across industries. However, their unpredictability raises significant concerns about data security and privacy. Developers struggle to ensure the integrity […]
Pierluigi Paganini
July 11, 2024
The US and its allies disrupted an AI-powered Russia-linked bot farm on the social media platform X relying on the Meliorator AI software. The U.S. FBI and Cyber National Mission Force, along with Dutch and Canadian intelligence and security agencies, warned social media companies about Russian state-sponsored actors using covert AI software, Meliorator, in disinformation […]
Pierluigi Paganini
July 04, 2024
Brazil’s data protection authority temporarily banned Meta from using data originating in the country to train its artificial intelligence. Brazil’s data protection authority, Autoridade Nacional de Proteção de Dados (ANPD), has imposed a temporary ban on Meta from processing users’ personal data for training its artificial intelligence (AI) models. “The National Data Protection Authority (ANPD) issued […]
Pierluigi Paganini
June 05, 2024
Cybersecurity researchers demonstrated how malware could potentially steal data collected by the new Windows Recall tool. The Recall feature of Microsoft Copilot+ is an AI-powered tool designed to help users search for past activities on their PC. The data collected by the tool is stored and processed locally. After its presentation, it raised security and […]
Pierluigi Paganini
May 24, 2024
UK data watchdog is investigating Microsoft regarding the new Recall feature in Copilot+ PCs that captures screenshots of the user’s laptop every few seconds. The UK data watchdog, the Information Commissioner’s Office (ICO), is investigating a new feature, called Recall, implemented by Microsoft” Copilot+ PCs that captures screenshots of the user’s laptop every few seconds. […]
Pierluigi Paganini
April 30, 2024
The US government’s cybersecurity agency CISA published a series of guidelines to protect critical infrastructure against AI-based attacks. CISA collaborated with Sector Risk Management Agencies (SRMAs) and regulatory agencies to conduct sector-specific assessments of AI risks to U.S. critical infrastructure, as mandated by Executive Order 14110 Section 4.3(a)(i). The analysis categorized AI risks into three […]
Pierluigi Paganini
April 09, 2024
China-linked threat actors are using AI to carry out influence operations aimed at fueling social disorders in the U.S. and Taiwan. China is using generative artificial intelligence to carry out influence operations against foreign countries, including the U.S. and Taiwan, and fuel social disorders. According to the report published by the Microsoft Threat Analysis Center […]
Pierluigi Paganini
February 23, 2024
Microsoft has released an open-access automation framework, called PyRIT, to proactively identify risks in generative artificial intelligence (AI) systems. Microsoft has released a Python Risk Identification Tool for generative AI (PyRIT), it is an open-access automation framework to proactively find risks in generative AI systems. The tool aims at helping red teaming activity of AI systems, Microsoft […]
