LLMs are everywhere in your stack and every layer brings new risk
LLMs are moving deeper into enterprise products and workflows, and that shift is creating new pressure on security leaders. A new guide from DryRun Security outlines how these …
AI-driven threats are heading straight for the factory floor
In this Help Net Security interview, Natalia Oropeza, Chief Cybersecurity Officer at Siemens, discusses how industrial organizations are adapting to a shift in cyber risk …
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. …
The simple shift that turns threat intel from noise into real insight
In this Help Net Security video, Alankrit Chona, CTO at Simbian, explains how security teams can put threat intelligence to work in a way that supports detection, response, …
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 …
CISOs are spending big and still losing ground
Security leaders are entering another budget cycle with more money to work with, but many still feel no safer. A new benchmark study from Wiz shows a widening gap between …
What security leaders should watch for when companies buy or sell a business
In this Help Net Security video, Lane Sullivan, SVP, CISO and Strategy Officer at Concentric AI, explains what security leaders should think about during mergers, …
AI vs. you: Who’s better at permission decisions?
A single tap on a permission prompt can decide how far an app reaches into a user’s personal data. Most of these calls happen during installation. The number of prompts keeps …
Attackers keep finding new ways to fool AI
AI development keeps accelerating while the safeguards around it move on uneven ground, according to The International AI Safety Report. Security leaders are being asked to …
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 …
Criminal networks industrialize payment fraud operations
Fraud operations are expanding faster than payment defenses can adjust. Criminal groups function like coordinated businesses that develop tools, automate tasks, and scale …
New “HashJack” attack can hijack AI browsers and assistants
Security researchers at Cato Networks have uncovered a new indirect prompt injection technique that can force popular AI browsers and assistants to deliver phishing links or …
Featured news
Resources
Don't miss
- Attackers plant remote access tools on compromised PaperCut servers
- Anthropic locks out Claude users after infostealers hijack login sessions
- What vulnerability prioritization looks like when KEV, EPSS, and CVSS disagree
- Halo-record: Open-source audit trails for AI agents
- What 90 days and a small budget can buy in AI agent security