Resources: Navigating the AI Security Landscape

A range of resources including research papers, webinars, and company news focused on AI Security.

Introducing Mindgard MITRE ATLAS™ Adviser

MITRE ATLAS™ Adviser in Mindgard that helps standardise AI red teaming reporting.

Modern AI Red Teaming: Probabilities, Vulnerabilities, and Psychometrics

A technical exploration of modern AI red teaming, examining how probabilistic behavior, classic vulnerabilities, and psychometric steering combine to create real-world AI security risk.

Bringing AI Security into Your CI/CD with Mindgard

Mindgard’s GitHub Action example repository shows how to integrate automated AI security testing into CI/CD pipelines so every model or code change is validated against the latest Mindgard capabilities.

Continuous AI Red Teaming: Why S&P Global Says It’s Critical to Securing the AI Era

S&P Global Coverage Initiation: Mindgard’s continuous AI red teaming looks to secure models and applications

PINCH framework: mapping how model stealing attacks really work

PINCH is an automated framework that runs large-scale extraction attacks across deep learning architectures to reveal how and when model stealing actually succeeds.

Model Leeching: cheaply cloning LLM skills for attack staging

Model Leeching shows how attackers can distill ChatGPT-class task knowledge into smaller models for about fifty dollars, then use them to tune follow on attacks.

Bypassing LLM guardrails: character and AML attacks in practice

This study shows how simple character transformations and algorithmic evasion attacks can silently bypass six popular LLM guardrails, sometimes reaching one hundred percent evasion.

Compilation as defense: using tensor optimizations to confuse attackers

This work shows how applying compiler driven tensor optimizations can cut side-channel model reconstruction success by up to forty-three percent without redesigning architectures.

Webinar: Prompt. Inject. Shell. Repeat - Exploiting Blind Spots within AI Guardrails

AI guardrails are often used as the first line of defense within AI systems, however how effective are they in practice against actual attackers?

Hunting AI Application Vulnerabilities With Burp

In this article we’ll walk through hunting for AI application vulnerabilities. We’ll use Mindgard to find application vulnerabilities in a deliberately-vulnerable LLM lab application made available by PortSwigger.

Analyst Report: OWASP LLM and Generative AI Security Solutions Landscape

The LLM and Generative AI Security Solutions Landscape is an industry report developed by OWASP that maps out key vendors and solutions in the AI security space. This landscape provides a comprehensive view of tools and technologies that help organizations safeguard their AI-powered applications.

Research: Shadow AI is a Blind Spot in Enterprise Security, Including Among Security Teams

At RSA Conference 2025 and InfoSecurity Europe 2025 we surveyed over 500 cybersecurity professionals to assess emerging threats in enterprise environments. The findings reveal a growing and often overlooked risk: security professionals using generative AI tools without approval, a trend known as Shadow AI.

Talk: Deconstructing AI Risk — From Research to Real-World Exploits

In this talk, Peter Garraghan demonstrates how adversaries are already exploiting AI systems and why current security practices are often ill-equipped to stop them.

Webinar: Test AI Systems, Not Models

In this webinar, Dr. Peter Garraghan takes the audience on a deep dive into the underbelly of AI vulnerabilities, exposing the gaps within traditional AI security approaches and demonstrating why application-level AI security must be a priority.

Analyst Report: Gartner AI TRiSM Market Guide

Gartner's AI Trust, Risk, and Security Management (AI TRiSM) framework provides a structured approach to managing AI risks while maintaining transparency and accountability.