-
A newly discovered vulnerability in the AI supply chain—termed Model Namespace Reuse—permits attackers to achieve Remote Code Execution (RCE) across major AI platforms, including Microsoft Azure AI Foundry, Google Vertex AI, and thousands of open-sourc…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
More than 1,100 instances of Ollama—a popular framework for running large language models (LLMs) locally—were discovered directly accessible on the public internet, with approximately 20% actively hosting vulnerable models that could be exploited by un…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A cutting-edge penetration testing tool called BruteForceAI has arrived, bringing automation and artificial intelligence to the art of login page detection and brute-force attacks. Designed for security professionals and researchers, BruteFor…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Within hours of its release, the newly unveiled framework Hexstrike-AI has emerged as a game-changer for cybercriminals, enabling them to scan, exploit and persist inside targets in under ten minutes. Hexstrike-AI, a red-team tool, quickly tu…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Researchers have demonstrated that advanced prompt injection techniques can turn defensive AI agents into potent vectors for system compromise. The findings, detailed in a new preprint titled “Cybersecurity AI: Hacking the AI Hackers via Prompt Injecti…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
A sophisticated new malware campaign has emerged that weaponizes artificial intelligence and social engineering to target niche online communities. Security researchers have identified the “AI Waifu RAT,” a remote access trojan that masquer…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Anthropic, a leading AI research company, has successfully disrupted multiple attempts by cybercriminals to misuse its Claude AI model for sophisticated cyberattacks, as detailed in their latest Threat Intelligence report. The company has implemented a…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
PromptLock, a novel ransomware strain discovered by the ESET Research team, marks the first known instance of malware harnessing a local large language model to generate its malicious payload on the victim’s machine. Rather than carrying pre-compiled a…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
Cybersecurity landscapes are undergoing a paradigm shift as threat actors increasingly deploy agentic AI systems to orchestrate sophisticated social engineering attacks. Unlike reactive generative AI models that merely produce content such as deepfakes…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
-
CYFIRMA researchers have uncovered a campaign they have codenamed “OneFlip”, an operation that demonstrates how a single-bit modification inside a seemingly benign file can be enough to re-pivot a neural-network-driven security workflow and open a back…
¶¶¶¶¶
¶¶¶¶¶
¶¶¶¶¶
