🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

AI-Driven Deepfake Detection via Evasion Attacks Check out our latest blog on: ◾️How adversaries can bypass #deepfake detection using AI models. ◾️AI red teaming of deep fake detection ◾️Robust defense mechanisms 👉bit.ly/46z6IE9 #AI #cybersecurity #redteaming

Check out this episode of CyberWire Daily, by N2K podcast with our co-Founder and CEO, Peter Garraghan , to learn more about tackling #cybersecurity risks for #AI 👇

Our team Mindgard have made some of our image model security tests available in our free AI Security Labs. See how secure your predictive AI models are against evasion attacks vs our example models. More details: mindgard.ai/resources/ai-r…

Mindgard have been recognized as one of the Top 10 London Startups Disrupting Industries🚀 Proud to be part of #London's #startup ecosystem 🇬🇧 A big kudos to our incredible team, partners, and all who are on this journey with us bit.ly/4dpJ3bK #Cybersecurity #AI

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

Check out this Raconteur article with commentary from Peter Garraghan, Mindgard's co-founder and CEO, to learn more about #AIsafety compliance for your organisation

🔴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

Mindgard's CEO Peter Garraghan shared his perspective on #AISecurity strategies with Help Net Security - check out the article and share your thoughts!

That’s a wrap on ICE_Expo #ICE2024 For two days our team, alongside our founders Peter Garraghan & Steve Street, have been on hand to show #security leaders how we can protect their most critical #AI assets Try us here mindgard.ai/try #CyberSecurity #AISecurity

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

Celebrating success 🏆 The CyberASAP programme’s alumni have raised over £32m, highlighting the real-world impact of academic #cybersecurity research. Find out more 🔗 iuk.ktn-uk.org/news/cyberasap… Department for Science, Innovation and Technology Mindgard KETS Quantum @capslockcyber Lupovis @osneycapital

Our CEO & co-founder Peter Garraghan shared his insights on security vulnerabilities in neural networks with EM360Tech podcast - check it out on Spotify: open.spotify.com/episode/5l4Pyn…

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

By me CSOonline Security researchers circumvent Microsoft Azure AI Content Safety csoonline.com/article/359326… (HT Mindgard) #AI #Hacking

🛡️ 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…

What many people don’t realize, is that the malicious use of #AIdeepfakes extends well beyond the political realm. To learn more about the threat and how businesses can protect themselves, check out this new article by Peter Garraghan, Mindgard's CEO and co-founder #AIsecurity

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

🚨 AI Red Teaming: Stress-Testing AI Systems for Enhanced Security Join our Co-founder & CEO Peter Garraghan at Black Hat to discuss the critical role of #redteaming in identifying #vulnerabilities and enhancing #AISecurity bit.ly/3Ztqi1n #BHEU

Are you in New York on the 11th and 12th Dec and keen to chat on #AIsecurity? Then don’t miss the chance to meet Mindgard's co-founder Steve Street at The AI Summit Series NY 2024. Book the meeting👇 mindgard.ai/ai-summit-new-… #TheAISummit

What is Gartner AI TRiSM (Trust, Risk, and Security Management)? The latest edition of the Market Guide is here! mindgard.ai/blog/gartner-a… #AI #TRiSM #Security