AI Security Blog

You'll find useful content about AI security, the cybersecurity landscape, news, events and much more updated regularly here.

Ghosts in the Machine: ASCII Smuggling across Various LLMs

Ghosts in the Machine: ASCII Smuggling across Various LLMs

Researcher Viktor Markopoulos discovers ASCII Smuggling bypasses human audit via Unicode, enabling enterprise identity spoofing and data poisoning on Gemini & Grok.

Subscribe to receive articles directly in your inbox

If you prefer to be notified of new posts via email, simply subscribe to our blog below.

Latest articles

All
OWASP LLM TOP 10
All
AI Security
All
Product
All
A View from the C-Suite
All
Fintech
All
cloud security
All
AI
All
Awards
All
API economy
All
podcast
All
WAF
All
Events
All
Cybersecurity
All
Cyber landscape
All
Company
All
API security
When AI Turns Against Us
June 4, 2025

When AI Turns Against Us

Computers going rogue used to be the stuff of science fiction. But in 2025, it is becoming real. Join us in this blog as we investigate some cases where Artificial Intelligence has behaved like it has a mind of its own…

Read more
The Sequential Kill Chain for AI
May 30, 2025

The Sequential Kill Chain for AI

We’ve talked before about Mean Time To Attack, or MTTA, which has grown alarmingly short for new vulnerabilities across the cyber landscape. In this blog, we’ll dive into the “how” and “why” of this…

Read more
Your Mobile Apps May Not Be as Secure as You Think…
May 28, 2025

Your Mobile Apps May Not Be as Secure as You Think…

Cybersecurity risks are too close for comfort. Recent data from the Global Mobile Threat Report reveals that our mobile phone applications are most likely exposing our data due to insecure practices such as API key hardcoding.

Read more
LLM03: Supply Chain
May 21, 2025

LLM03: Supply Chain

The OWASP Top 10 List of Risks for LLMs helps developers and security teams determine where the biggest risk factors lay. In this blog series from FireTail, we are exploring each risk one by one, how it manifests, and mitigation strategies. This week, we’re focusing on LLM03: Supply Chain vulnerabilities.

Read more
Closing the Loop: Continuous API Security Testing
May 14, 2025

Closing the Loop: Continuous API Security Testing

APIs power all of the connections we take for granted in the modern internet. But as we rely on them more for new technologies like AI, securing them is harder than ever. That’s why continuous API security testing is an essential part of every cybersecurity posture.

Read more
Logging AI before it happens
May 14, 2025

Logging AI before it happens

Did you know that some AI chats capture and log your chat before you even submit it? This creates a huge security problem for both individuals and organizations whose employees use LLMs. Luckily, FireTail is working on a solution...

Read more