I’m attending Black Hat in Mandalay Bay/Las Vegas August 3-8. Feel free to DM me if you'd like to meet up and discuss all matters Mindgard and #AIsecurity related. You can also request to meet via this link: bit.ly/3WOHyOA #BHUSA #cybersecurity #infosec

AI-driven #deepfake detection can be easily bypassed using evasion attacks. How? Find out in our latest article from the @Mindgard team bit.ly/46z6IE9 Try #AI Red Teaming this deepfake scenario yourself for free by using Mindgard AI Security Labs bit.ly/3WBlWnp

Had a pleasure to talk with Dave Bittner @[email protected] for The Caveat Podcast from CyberWire Daily, by N2K about: 📰@Mindgard's role in the UK's #AIsecurity guidelines 🛡️Key recommendations for tackling risks in #AI 🚀Challenges & future of AI in #cybersecurity 🎧 Full episode: bit.ly/3yx9g96

Thank you to everyone who took the time to chat with me at Black Hat 2024. Great to meet new folks as well as catch up familiar faces in #AIsecurity @Mindgard #BHUSA #cybersecurity #AI

How does one put reasonable controls on something designed to be intrinsically random? Shared my thoughts with Jasper Hamill on the safety concerns of LLM models for scientific research or other activities Check out this The Stack article: bit.ly/4dt7CVs

Well done, Mindgard team!

RAG models indeed have a #security issue inherent in how they operate. Discover more in my commentary for The Stack article on #Microsoft's RAG Copilot vulnerabilities. Jasper Hamill, thanks for the great piece! bit.ly/478pfYl #AISafety #LLMs #AI

Could #AI be your company’s Achilles heel? Indeed. Vulnerabilities in #LLMs may pose an even greater threat to organisations than AI-powered assaults Shared my thoughts on this topic with Raconteur Check out the article via the link bit.ly/3AzJYYQ #cybersecurity

No matter how you look at it, #AI is currently booming. The problem is that hasty integration and innovation opens the AI to #cybersecurity risks that can cause serious financial and reputational damage. Read more in my opinion article for BetaNews.com bit.ly/47dpwJz

🔴Are your #AISystem secure? Mindgard team explores 6 key adversarial attacks and explain their mechanisms, potential consequences & defense strategies. Check out this blog to gain more insights on #AIsecurity bit.ly/3XdXxoh #cybersecurity #AI

The #LLMs rise created an alarming increase in AI-enabled attacks. AI #cybersecurity needs to be as multi-layered as the systems it's protecting. Read more on #AISecurity strategies in my article for Help Net Security bit.ly/3zgbjie

Big kudos to all who stopped by our booth on ICE_Expo and joined us to explore how Mindgard 🔐 Automates Vulnerability Scanning of AI assets 🔐 Continuously secures GenAI & LLM applications 🔐 Safeguards Image, Audio & NLP models #ICE2024 #cybersecurity #RedTeaming

If you're interested in learning more about #AIwashing, here's my recent article for CyberDefenseMagazine on ▪️What is AI washing and how it came to be ▪️How #AI encompasses more than #ChatGPT ▪️Risks to organizations partaking in AI washing Check it out: bit.ly/4ehBzIm

Thank you Paulina Rios-Maya for inviting me to speak on EM360Tech's Security Strategist Podcast! We explored #cybersecurity risks to #AI, focusing on security vulnerabilities in neural networks—challenges that Mindgard is tackling. Listen to the episode here: bit.ly/em360tech

In case you didn’t know: our company, Mindgard, spun out of Lancaster University in 2022. Recently had an insightful talk on the subject for Tech EU podcast w/ Kevin Berghoff, CEO of QuantumDiamonds Big kudos to john reynolds for the invite! bit.ly/40ftShD

🛡️ Mindgard discloses two security #vulnerabilities within Microsoft Azure AI Content Safety They enable attackers to bypass #genAI guardrails to push malicious content onto protected #LLM Read more in CSOonline - John Leyden, thanks for the article! csoonline.com/article/359326…

#AI Deepfakes is a serious #cybersecurity threat for businesses and one that not enough #enterprises are protected against. A holistic approach is essential—and that’s exactly what we’re developing at Mindgard Read more in my article for AI Business aibusiness.com/generative-ai/…

Commented for Forbes on the dangers of poorly trained #AI The recent story of Google Gemini outputting harmful content to its users highlights the #risks of operating #LLMs and the critical need for continuous testing of models and their guardrails bit.ly/3V6YwXi

The AI Summit Series will join #BHEU for the first time! See you there! Black Hat

What CISOs should consider when integrating #GenAI into their security operations? Read in this excellent CSOonline article by John Leyden, with my take on the topic as well #AISecurity Mindgard