Author | Lightnews

HiddenLayer

@hiddenlayer.bsky.social

HiddenLayer helps enterprises safeguard the AI models behind their most important products with a comprehensive security platform. #Security4AI

Posts Replies Media Videos

Reposted by HiddenLayer

Help Net Security

@helpnetsecurity.com

Securing agentic AI systems before they go rogue

🎥 Link to the video: www.helpnetsecurity.com/2025/06/10/s...

#cybersecurity #cybersecuritynews #agenticAI @hiddenlayer.bsky.social

Securing agentic AI systems before they go rogue - Help Net Security

This video breaks down how agentic AI functions, its potential to revolutionize business operations, and the vulnerabilities it introduces.

www.helpnetsecurity.com

June 10, 2025 at 8:45 AM

HiddenLayer

@hiddenlayer.bsky.social

We recently published research on a universal prompt injection bypass across all major LLMs, demonstrating cross-architecture vulnerabilities without model access.
Would love your thoughts on whether improved architectures (vs. alignment alone) can mitigate these. @yann-lecun.bsky.social

April 25, 2025 at 6:07 PM

HiddenLayer

@hiddenlayer.bsky.social

🚨 HiddenLayer in Forbes: One prompt bypasses safety on OpenAI, Google, Anthropic, & more. It is model-agnostic and transfers across LLMs. Alignment isn’t enough. Security must evolve.

📰 Forbes: www.forbes.com/sites/tonybr...
📖 Research: hiddenlayer.com/innovation-h...

#SecureAI #PromptInjection

One Prompt Can Bypass Every Major LLM’s Safeguards

Researchers have discovered a universal prompt injection technique that bypasses safety in all major LLMs, revealing critical flaws in current AI alignment methods.

www.forbes.com

April 25, 2025 at 5:30 PM

HiddenLayer

@hiddenlayer.bsky.social

📅 SAVE THE DATE: HiddenLayer’s 2024 AI Threat Landscape Report will be released on March 6th. Sign up to be the first to preview the report & join us in a webinar discussion as we share some of the report’s most important findings 👉 hiddenlayer.com/threatreport...
#Security4AI