Sinisa Markovic
When AI agents interact, risk can emerge without warning
System level risks can arise when AI agents interact over time, according to new research that examines how collective behavior forms inside multi agent systems. The study …
Gen AI data violations more than double
Security teams track activity that moves well beyond traditional SaaS platforms, with employees interacting daily with generative AI tools, personal cloud services, and …
Turning plain language into firewall rules
Firewall rules often begin as a sentence in someone’s head. A team needs access to an application. A service needs to be blocked after hours. Translating those ideas into …
Passwords are still breaking compliance programs
The security stack has grown, but audits still stumble on passwords. CISOs see this every year. An organization may have strong endpoint tools, layered network defenses, and a …
OpenAEV: Open-source adversarial exposure validation platform
OpenAEV is an open source platform designed to plan, run, and review cyber adversary simulation campaigns used by security teams. The project focuses on organizing exercises …
From experiment to production, AI settles into embedded software development
AI-generated code is already running inside devices that control power grids, medical equipment, vehicles, and industrial plants. AI moves from experiment to production AI …
Duplicati: Free, open-source backup client
Duplicati is an open source backup client that creates encrypted, incremental, compressed backup sets and sends them to cloud storage services or remote file servers. What the …
Illegal streaming grew into an organized, profitable, and dangerous industry
Rising streaming prices are pushing more viewers toward illegal options. Movies, TV shows, and live sports are now spread across multiple platforms, and keeping up with all of …
Security coverage is falling behind the way attackers behave
Cybercriminals keep tweaking their procedures, trying out new techniques, and shifting tactics across campaigns. Coverage that worked yesterday may miss how those behaviors …
Radio signals could give attackers a foothold inside air-gapped devices
Air-gapped systems are meant to stay quiet. Remove network ports, lock down inputs, and the device should have nothing to hear. A new study shows that this breaks down when …
Non-human identities push identity security into uncharted territory
Enterprises are grappling with an identity attack surface that keeps expanding and slipping out of reach, according to Veza. Permissions growth outstrips oversight Permissions …
LLMs are automating the human part of romance scams
Romance scams succeed because they feel human. New research shows that feeling no longer requires a person on the other side of the chat. The three stages of a romance-baiting …