“Why pay for a VPN when there are so many free ones available?” While many people choose to rely on free VPN services, driven by the promise of anonymity and security, few know the risks that lie…
A recent study quantified the security properties of AI-generated code across a range of programming languages and models. The focus of the study was to evaluate whether LLMs generate secure code in…
MALLAs are applications that integrate the use of Large Language Models specialized in generating and automating cyberattacks. Dive into their ecosystem, promotion strategies, main mitigation…
Cybercriminals today use a technique called steganography to hide malware inside image files, bypassing antivirus checks and successfully targeting even experienced users.
LLMs have several vulnerabilities that can be exploited by malicious users for illicit purposes. OWASP started ranking the major risks associated with the use of LLMs. Prompt Injection attacks were…
Gen Z might be the most digitally fluent generation yet, but they’re also becoming one of the most attractive targets for cybercriminals.It’s no longer about fake bank emails or Nigerian princes; it’s…
Cyber-attacks are more and more utilized in warfare. Wars are no longer fought only with traditional weapons: viruses, ransomware and spyware (to name a few) are used to target critical…
EchoLeak is the first zero-click vulnerability identified in an AI agent as Copilot. It leverages an advanced technique called LLM Scope Violation, allowing an attacker to extract confidential data…
Meta AI app has raised serious privacy concerns, as user conversation, often containing sensitive information, are being made public without users’ full awareness. Both the standalone app and Meta’s…
