Posts tagged "ai

AI Security Jun 25, 2025

Building a Secure AI Chatbot for Internal Search: Lessons from NIST’s NCCoE

Technical and Security Lessons from the initial NIST’s NCCoE chatbot implementation

ai

Read more →

AI Security Jun 20, 2025

Living off AI POC Attack: Exploiting MCP Integrations Through Prompt Injection

Research looks at how threat actors could potentially exploit Model Context Protocol integrations to gain privileged access through support tickets

ai

Read more →

AI Security Jun 16, 2025

Securing LLMs: Why Traditional AppSec Approaches Don't Work

Why traditional AppSec approaches don't work for LLMs, and how to secure them.

ai

Read more →

AI Security Jun 16, 2025

Securing Your LLM Supply Chain: From Models to Dependencies

Article exploring supply chain security risks and dependencies for LLMs

ai

Read more →

AI Security Jun 15, 2025

The Dual LLM Pattern for LLM Agents

ai

Read more →

AI Security Jun 15, 2025

The Context-Minimisation Pattern for LLM Agents

ai

Read more →

AI Security Jun 15, 2025

The Plan-Then-Execute Pattern for LLM Agents

ai

Read more →

AI Security Jun 15, 2025

The LLM Map-Reduce Pattern for LLM Agents

ai

Read more →

AI Security Jun 15, 2025

The Code-Then-Execute Pattern for LLM Agents

ai

Read more →

AI Security Jun 13, 2025

The Action-Selector Pattern for LLM Agents

ai

Read more →

AI Jun 11, 2025

Prompt Injection 101 - Risks and Defences

Learn about prompt injection, how it works, the risks involved, and how to defend against it.

ai

Read more →

AI Jun 4, 2025

LLM Jailbreaking Explained: Attack Methods, Real Risks, and Defences

Learn about LLM jailbreaking, how it works, the risks involved, and how to defend against it.

ai

Read more →

AI Jun 2, 2025

Shadow AI: Is Your Company Data at Risk?

Learn about Shadow AI, why employees use unapproved AI tools, the risks involved for businesses, and how to address it.

ai

Read more →

Security Insights May 19, 2025

Security Insights: Insider Threats, Multi‑Actor Campaigns and the Race to Mitigate

Key security developments shaping cyber defence, from AI-enabled attacks to supply-chain compromises.

ai threat intelligence

Read more →

Security Insights May 9, 2025

Security Insights: Identity Evolved, Supply Chain Risks & Active Exploits

A curated collection of security developments and research from across the industry, with practical insights and analysis.

ai threat intelligence

Read more →

Security Insights May 2, 2025

Security Insights: Zero-Days, APTs and AI Risks

A curated collection of security developments and research from across the industry, with practical insights and analysis.

ai threat intelligence

Read more →

AI Security Apr 30, 2025

LlamaFirewall: AI Agent Open-Source Guardrail System

An overview of LlamaFirewall, an open-source guardrail system for AI agents, detailing its components: PromptGuard 2, AlignmentCheck, and CodeShield.

ai

Read more →

AI Security Apr 19, 2025

Hands-On with the Agent Development Kit (ADK): A Security Triage PoC

A first look at the Google Agent Development Kit (ADK), testing its multi-agent delegation capabilities with a security alert triage Proof-of-Concept.

ai

Read more →

AI Security Apr 6, 2025

The AI Security Balance: Criminal Exploitation vs. Defensive Innovation

Examines the dual use of AI in security, covering criminal exploitation tactics highlighted by the Alan Turing Institute and defensive advancements like Google Sec-Gemini v1.

ai cybersecurity threat intelligence +5 more

Read more →

Cybersecurity Mar 21, 2025

Actionable Defences Against AI-Powered Phishing

Learn how AI is transforming phishing attacks and discover practical strategies to protect your organisation against sophisticated AI-powered social engineering attempts.

phishing ai threat modeling

Read more →

AI Security Mar 20, 2025

MCP Security 101: Exploring AIs Universal Connector

Explore how the Model Context Protocol works as a universal connector for AI systems, and security considerations when implementing it.

mcp ai

Read more →