cybersecurity
A nearly undetectable LLM attack needs only a handful of poisoned samples
Prompt engineering has become a standard part of how large language models are deployed in production, and it introduces an attack surface most organizations have not yet …
Your facilities run on fragile supply chains and nobody wants to admit it
In this Help Net Security interview, Christa Dodoo, Global Chair at IFMA, discusses how facility managers are managing supply chain risk in critical building systems. She …
Who owns AI agent access? At most companies, nobody knows
AI agents are operating across production enterprise environments at scale, and the identity infrastructure managing their access has not kept up with their deployment. A …
Gemini picks up criminal activity buried in dark web noise
To help teams make faster and more accurate decisions on emerging threats, Google has introduced a dark web intelligence capability in Google Threat Intelligence. Powered by …
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 …
Why your phishing simulations aren’t building a security culture
Security culture isn’t built by phishing simulations. In this Help Net Security video, Dan Potter, VP of Cyber Resilience at Immersive, argues that annual training …
Your security stack looks fine from the dashboard and that’s the problem
One in five enterprise endpoints is operating outside a protected and enforceable state on any given day, according to device telemetry collected across tens of millions of …
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 …
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 …
Attackers are handing off access in 22 seconds, Mandiant finds
Exploits remain the leading entry point for attackers for the sixth consecutive year, according to Mandiant’s M-Trends 2026 report, which draws on more than 500,000 …
Quantum threats are already active and the defense response remains fragmented
Enterprises are moving toward post-quantum security at uneven speeds, and the gap between organizations that have built crypto-agility into their infrastructure and those that …
The devices winning the race to get hacked in 2026
Enterprise networks keep adding connected devices, expanding the attack surface as threat actors target a wider range of systems, many of which are difficult to inventory, …
Featured news
Resources
Don't miss
- Social engineering attacks on open source developers are escalating
- Chaos malware expands from routers to Linux cloud servers
- What managing partners should ask AI vendors before signing any contract
- Anthropic’s new AI model finds and exploits zero-days across every major OS and browser
- Comp AI: The open-source way to get compliant with SOC 2, ISO 27001, HIPAA and GDPR