HiddenLayer helps enterprises safeguard the AI models behind their most important products with a comprehensive security platform
Austin, TX
Joined July 2022
- Tweets475
- Following24
- Followers895
- Likes313
🎥 Missed it live? Catch the replay of our webinar on the taxonomy of adversarial prompt engineering.
Learn how to break down LLM prompt attacks by objectives, tactics, and techniques and why it matters for real defense.
🔗 Watch here: youtube.com/watch?v=EMvM8tmm…
#AISecurity
🚨 Join our live walkthrough of @hiddenlayersec's new taxonomy of adversarial prompt engineering, a framework for classifying & combating prompt-based attacks against LLMs.
⏰ June 25th, 11am CST
🔗 Register here: hiddenlayer.zoom.us/webinar/…
🚨HiddenLayer’s Director of Adversarial Research, Jason Martin, joins The Data Exchange Podcast to talk about what it takes to actually defend LLMs.
🎙️ Beyond Guardrails: Defending LLMs Against Sophisticated Attacks.
Stream now: youtube.com/watch?v=L9MXnBeH…
New on the AI Engineering Podcast: HiddenLayer’s Kasimir Schulz breaks down how to secure ML models from shadow logic & model ancestry to scanning for threats.
-Scan models
-Trace neural subgraphs
-Know your attack surface
Listen here: podcasts.apple.com/us/podcas…
#AIsec #MLSec #AI
The 2025 AI Threat Landscape Report is here. Our latest report breaks down the real-world tactics attackers are using against AI, the emerging risks organizations need to know, and how security teams can stay ahead without slowing innovation.
🔗 hiddenlayer.com/threatreport…
HiddenLayer has been recognized in @FastCompany 2024 Next Big Things in Tech Awards in the Security & Privacy category. Thank you to our team & supporters who believe in our mission to make security for AI safer, smarter, and stronger. Read more here: hiddenlayer.com/research/hid…
HiddenLayer has been named a Gartner® Cool Vendor in AI Security! We believe being named a Gartner Cool Vendor reaffirms that our approach and solutions are on the right path.
Download the report here: hiddenlayer.com/hiddenlayer-…
Read our press release here: hiddenlayer.com/company/news…
Our latest research highlights that even well-intentioned solutions can have vulnerabilities. We found that the watermarking service used by AWS to combat misinformation in digital content generated by its Titan AI model had a vulnerability. Read more 👉 hiddenlayer.com/research/att…
New Research: New Gemini for Workspace Vulnerability Enabling Phishing and Content Manipulation. Our latest blog examines vulnerabilities in Google’s Gemini for Workspace, a versatile AI assistant.
🔗 Read more: hiddenlayer.com/research/new…
