AI security
Kaspersky Releases Guidelines on Securing AI Agents with Cyber Immunity
Kaspersky has issued new Cyber Immunity guidelines to help organizations secure autonomous AI agents against operational and digital threats.
SSICT News ·
Latest News
AmiViz to Showcase AI Security and Digital Tech at LEAP 2026
AmiViz will showcase AI security, sovereign cloud, and data resilience technologies at LEAP 2026 in Riyadh to support Saudi digital infrastructure.
Researchers Extract Hidden Reasoning Traces From Leading AI Models
Researchers have uncovered a method to extract hidden reasoning steps from major AI models, raising security and data distillation concerns.
Nvidia Leads Formation of Open Secure AI Alliance Following OpenAI Security Incident
Nvidia has led the formation of the Open Secure AI Alliance alongside Microsoft, SpaceX, and Cisco to build open defensive tools following the recent OpenAI security incident.
NVIDIA and Microsoft Launch Open Secure AI Alliance to Combat Digital Threats
NVIDIA and Microsoft have established a new global alliance to develop open-source security tools for artificial intelligence systems.
OpenAI Takes Responsibility for Hugging Face Security Breach
OpenAI has admitted that its pre-release models escaped an isolated testing sandbox to hack Hugging Face due to a configuration error.
- Ad
New HalluSquatting Attack Exploits Popular AI Coding Tools to Build Botnets
Security researchers have uncovered a new vulnerability called HalluSquatting that allows attackers to hijack AI coding assistants and build massive botnets.
Saudi Arabia Releases 42 AI Security Guidelines for Tech Systems
The Saudi National Cybersecurity Authority has launched a draft framework with 42 guidelines to secure artificial intelligence systems from cyberattacks.
AI-Assisted Attack Exposes Millions of Hotel Records
A security investigation has revealed how a Russian hacker used AI tools to breach multiple hotel booking platforms, exposing millions of guest records.
Anthropic Accuses Alibaba of Massive Distillation Attack on Claude AI
Anthropic has accused Alibaba of executing the largest known distillation attack on its Claude AI model, generating millions of unauthorized exchanges.
Five Eyes Alliance Warns of Accelerating AI Cyber Threat
The Five Eyes alliance warns that the AI cyber threat is accelerating the speed and scale of attacks, requiring immediate action from business leaders.
Rubrik Launches Rubrik Agent Cloud for Anthropic’s Claude Code
Rubrik has launched Rubrik Agent Cloud to secure Anthropic’s Claude Code, introducing real-time governance, agent rewind, and immutable codebase recovery.
Rubrik Launches AI Agent Management Platform for Anthropic Claude
Rubrik has launched its new AI Agent management platform for Anthropic’s Claude Code, introducing runtime protection and immediate rollback capabilities.
White House and Anthropic Negotiate Technical Standards for AI Models
The White House and Anthropic are negotiating technical standards to evaluate security flaws in advanced models following recent export controls.
NVIDIA Open-Sources SkillSpector to Secure AI Agent Skills
NVIDIA has released SkillSpector, an open-source security scanner designed to detect vulnerabilities and malicious code in AI agent skills before installation.
NVIDIA Announces Vera BlueField-4 STX Security Innovations for Agentic AI
NVIDIA has introduced new DOCA security features for the Vera BlueField-4 STX platform to protect data in agentic AI factories.
Anthropic Details Security Framework for Claude Models
Anthropic has detailed its security framework for Claude models, focusing on environment-level containment to prevent unauthorized data access.
Fortinet and NVIDIA Deepen Integration to Secure Enterprise AI with FortiAIGate
Fortinet and NVIDIA have launched FortiAIGate, a zero-trust security solution for enterprise AI workloads. The joint offering protects AI models, data, and autonomous agents across cloud and on-premises environments.
Microsoft’s MDASH System Finds 16 Windows Vulnerabilities Using AI Agents
Microsoft’s MDASH multi-model agentic system discovered 16 Windows vulnerabilities including four critical remote code execution flaws. The AI-powered tool scored 88.45% on the CyberGym benchmark and achieved 100% recall on five years of tcpip.sys security cases.
Cisco Introduces Security Solutions for Enterprise AI Agent Deployment
Cisco launched security solutions designed to enable enterprise adoption of AI agents at scale, addressing identity management, agent hardening, and threat detection across the agentic ecosystem.