Artificial intelligence
Google’s TurboQuant cuts AI memory use without losing accuracy
Large language models carry a persistent scaling problem. As context windows grow, the memory required to store key-value (KV) caches expands proportionally, consuming GPU …
Training an AI agent to attack LLM applications like a real adversary
Most enterprise software development teams now ship AI-powered applications faster than traditional penetration testing can keep up with. A security team with 500 applications …
The AI safety conversation is focused on the wrong layer
Organizations have spent years accumulating fragmented identity systems: too many roles, too many credentials, too many disconnected tools. For a workforce of humans, that …
32% of top-exploited vulnerabilities are over a decade old
Exploitation timelines continued to compress in enterprise environments, with newly disclosed flaws reaching active use almost immediately and older weaknesses remaining …
Microsoft details AI prompt abuse techniques targeting AI assistants
Prompt abuse occurs when crafted inputs manipulate an AI system into producing unintended behavior, such as attempting to access sensitive information or overriding built-in …
Measuring security performance in real-time, not once a quarter
Most organizations have invested heavily in security products over the past decade. The assumption embedded in that spending is that more tools equal better protection. Tim …
Your AI agents are moving sensitive data. Do you know where?
In this Help Net Security interview, Gidi Cohen, CEO at Bonfy.AI, addresses what he sees as the most pressing gap in AI agent security: data-layer risk. While the industry …
Fake AI songs streamed billions of times, netting fraudster $10 million
Michael Smith, 54, of Cornelius, North Carolina, has pleaded guilty in federal court to running a scheme that exploited music streaming platforms and diverted royalty payments …
AI got it wrong with high confidence. Now what?
In this Help Net Security interview, Christian Debes, Head of Data Analytics & AI at SPRYFOX, talks about the growing gap between what AI models do and what their …
Big tech companies step in to support the open source security ecosystem
Backed by new funding commitments from major technology players, open source security efforts are moving beyond threat identification toward practical solutions for defenders. …
Microsoft zeroes in on AI-driven data risks in Fabric
New Microsoft Purview innovations for Microsoft Fabric help organizations secure data and accelerate AI adoption. The updates focus on identifying risks, preventing data …
Hidden instructions in README files can make AI agents leak data
Developers rely on AI coding agents to set up projects, install dependencies, and run commands by following instructions in repository README files, which provide setup …
Featured news
Resources
Don't miss
- ClickFix campaign delivers Mac malware via fake Apple page
- Poisoned “Office 365” search results lead to stolen paychecks
- What vibe hunting gets right about AI threat hunting, and where it breaks down
- Health insurance lead sites sell personal data within seconds of form submission
- Claude helps researcher dig up decade-old Apache ActiveMQ RCE vulnerability (CVE-2026-34197)