Features
AI agents break rules in unexpected ways
AI agents are starting to take on tasks that used to be handled by people. These systems plan steps, call tools, and carry out actions without a person approving every move. …
NVIDIA research shows how agentic AI fails under attack
Enterprises are rushing to deploy agentic systems that plan, use tools, and make decisions with less human guidance than earlier AI models. This new class of systems also …
Building the missing layers for an internet of agents
Cybersecurity teams are starting to think about how large language model agents might interact at scale. A new paper from Cisco Research argues that the current network stack …
Smart grids are trying to modernize and attackers are treating it like an invitation
In this Help Net Security interview, Sonia Kumar, Senior Director Cyber Security at Analog Devices, discusses how securing decentralized smart grids demands a shift in …
A day in the life of the internet tells a bigger story
On any given day, the internet carries countless signals that hint at how networks behave behind the scenes. Researchers from RIPE NCC and several universities found a way to …
Creative cybersecurity strategies for resource-constrained institutions
In this Help Net Security interview, Dennis Pickett, CISO at RTI International, talks about how research institutions can approach cybersecurity with limited resources and …
Treating MCP like an API creates security blind spots
In this Help Net Security interview, Michael Yaroshefsky, CEO at MCP Manager, discusses how Model Context Protocol’s (MCP) trust model creates security gaps that many …
New observational auditing framework takes aim at machine learning privacy leaks
Machine learning (ML) privacy concerns continue to surface, as audits show that models can reveal parts of the labels (the user’s choice, expressed preference, or the result …
Heineken CISO champions a new risk mindset to unlock innovation
In this Help Net Security interview, Marina Marceta, CISO at Heineken, discusses what it takes for CISOs to be seen as business-aligned leaders rather than technical …
Small language models step into the fight against phishing sites
Phishing sites keep rising, and security teams are searching for ways to sort suspicious pages at speed. A recent study explores whether small language models (SLMs) can scan …
How an AI meltdown could reset enterprise expectations
In this Help Net Security interview, Graham McMillan, CTO at Redgate Software, discusses AI, security, and the future of enterprise oversight. He explains why past incidents …
Quantum encryption is pushing satellite hardware to its limits
In this Help Net Security interview, Colonel Ludovic Monnerat, Commander Space Command, Swiss Armed Forces, discusses how securing space assets is advancing in response to …
Featured news
Resources
Don't miss
- Radio signals could give attackers a foothold inside air-gapped devices
- Product showcase: RoboForm password manager for iOS
- LLMs are automating the human part of romance scams
- Superagent: Open-source framework for guardrails around agentic AI
- Security chaos engineering matters when nothing is broken