Microsoft has unveiled a comprehensive defense-in-depth strategy to combat indirect prompt injection attacks, one of the most significant security threats facing large language model (LLM)…
Cybersecurity researchers at Darktrace have uncovered a sophisticated attack targeting a US-based chemicals company, marking the first observed instance of threat actors exploiting SAP NetWeaver…
Jul 30, 2025Ravie LakshmananVulnerability / Threat Intelligence Threat actors have been observed exploiting a now-patched critical SAP NetWeaver flaw to deliver the Auto-Color backdoor in…
The UK’s AI Security Institute is collaborating with several global institutions on a global initiative to ensure artificial intelligence (AI) systems behave in a predictable…
A sophisticated cyberattack targeting a US-based chemicals company has revealed the first observed pairing of SAP NetWeaver exploitation with Auto-Color malware, demonstrating how threat actors…
Researchers at Avast have unveiled a free decryptor tool for victims of the FunkSec ransomware, marking a significant step in combating this now-defunct malware strain.…
The loosely connected network of threat actors behind several high profile hacks known as Scattered Spider has added new ransomware and improved social engineering techniques…
Enterprise applications integrating Large Language Models (LLMs) face unprecedented security vulnerabilities that can be exploited through deceptively simple prompt injection attacks. Recent security assessments reveal…
Microsoft has unveiled new guidance addressing one of the most pressing security challenges facing enterprise AI deployments: indirect prompt injection attacks. This emerging threat vector…
Identity-based attack paths are behind most breaches today, yet many organizations can’t actually see how those paths form. The 2025 State of Attack Path Management…
Optus will begin using a generative AI-powered virtual agent, co-developed with Google Cloud, to interpret and support contact centre staff interactions with customers. Named Expert…
Security researchers have discovered alarming vulnerabilities in enterprise Large Language Model (LLM) applications that could allow attackers to bypass authentication systems and access sensitive corporate…
