explore | Grilled Cheese

Prismor: Open-source runtime control plane for AI agents

#cybersecurity #cybersecuritynews #AIsecurity #AIagents #opensource #promptinjection

Blog post about what I think is a much more realistic AI cybersecurity problem than the usual “AI will hack everything” narrative:

paolozaino.wordpress.com/2026/09/21/a...

#AI #CyberSecurity #SoftwareSupplyChain #AISecurity #AppSec #LLM #Security #SoftwareEngineering #OpenSource

Full blog post coming, but Drosera now has Microsoft Sentinel and Defender integration

#AgenticAI #AISecurity #AIGovernance #AgentSecurity #CyberGovernance
https://go.rodtrent.com/go/cz998db

What is a perceptron?

It is a simple machine-learning model that combines weighted inputs and a bias to produce a classification.

AI security starts with understanding how a model reaches its answer.

Explore the Academy at learn.cylabacademy.org.

#AISecurity #MachineLearning

CVE-2026-33625 LMDeploy code injection, CVSS 8.8. Malicious HuggingFace model runs arbitrary Python via quant_dtype eval on load. No patch confirmed. Update to 0.12.3 now. https://www.valtersit.com/cve/CVE-2026-33625/ #CVE #infosec #AIsecurity

🤖 AI is powerful. But is your LLM application secure? Dive into the 𝗢𝗪𝗔𝗦𝗣 𝗧𝗼𝗽 𝟭𝟬 𝗳𝗼𝗿 𝗟𝗟𝗠 𝗔𝗽𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻𝘀 with hands-on challenges designed to help you understand real-world LLM security thre@ts.

👉🏻 infinity.cyberwarfare.live

#CWL #InfinityLearning #OWASP #LLMSecurity #AISecurity

Building AI products for enterprise use requires more than strong AI capabilities.

Explore the key requirements for building secure, enterprise-ready AI products:

writeupcafe.com/how-to-build...

#AIProductDevelopment #EnterpriseAI #AISecurity #AICompliance #AI #DataSecurity #AIGovernance

Participants bring a current AI security or privacy problem from their own work and examine it with senior peers from other companies.

Two live two-hour sessions each week for five weeks.

#AISecurity

Recent AI hacks and security breaches reveal surprising vulnerabilities in major companies. Seems the race for AI advancement may have outpaced robust security measures. #AIsecurity #cybersecurity

Google's Gemini AI Breached Real Companies During Secret Security Test

https://newisty.com/blog/googles-gemini-ai-breached-real-companies-during-secret-security-test?utm_source=social&utm_campaign=crypto_news

#gemini #google #aisecurity

When AI Becomes Part of the Threat Landscape

AI is creating new cyber risks.

🔹 Assess AI risks
🔹 Strengthen identity controls
🔹 Improve threat detection
🔹 Prepare for incidents

Stay prepared with Infosec K2K.

#InfosecK2K #AISecurity #CyberSecurity #IdentitySecurity

New Breach Please: an AI tool nearly triggered a military interdiction over a bad cargo flag. @malwarejake.bsky.social and I dig into what likely went wrong and why "human in the loop" often isn't real unless people feel safe pushing back.

youtu.be/mPDsf0x5JT8

#BreachPlease #AISecurity

Google's Gemini AI agents broke out of a "capture-the-flag" test and actually hacked three outside companies by guessing passwords. "Broke containment" is a phrase I did not want to hear about an AI. 😬 We need some serious guardrails here. #AI #AISecurity

Netragard CEO Adriel Desautels was featured in Business Insight on the cybersecurity mistakes that leave businesses exposed.

Our latest blog explores why compliance ≠ security and how AI accelerates existing attack paths.