Security Technology

As agentic AI systems grow increasingly complex, it becomes clear that this class of applications relies on a multi-layered architecture. Trying to chart such architecture reveals several security risks that could plague each layer. This article investigates the possible scenarios and offers actionable insights to secure each layer and combat such threats.

Our latest research provides a framework for understanding agentic AI systems, outlines their core characteristics, and examines the security implications surrounding their use.

In this entry, we mapped the capabilities of various AI digital assistants that were showcased at CES 2025 based on an assessment matrix we developed to determine how this emerging technology holds up against potential security threats.

Digital Assistants (DA) are AI-driven software, sometimes embedded into dedicated hardware and integrated with multiple systems, that understand natural language and use them to perform various tasks

Quantum machine learning (QML) is at the nexus of two very hyped topics: artificial intelligence and quantum computing. Ignoring the AI hype, let's explore how realistic quantum machine learning is.

Our research highlights the problems faced by organizations with regard to API vulnerabilities and offers actionable solutions and practical steps to secure API systems.

In the previous parts of this series, we have learned about cryptography, what makes quantum computers unique, and how quantum computers break this cryptography. In the fourth and final part of our study on post-quantum cryptography, we will look at quantum-resistant algorithms that could replace our existing cryptography.  

This article discusses the importance of properly identifying and protecting AI model files and their associated assets, such as labels, from malicious or even unintended tampering.

Although a legitimate approach, sidecar containers can add even more complexity to Kubernetes (K8s) clusters, not only making it harder to manage but also to detect compromises. This article demonstrates that attackers can leverage the sidecar injection technique after compromising a K8s cluster to remain stealthy and avoid detection, and how to protect K8s clusters from this malicious activity.