Home Authors Posts by Luca Sambucci

Luca Sambucci

28 POSTS 0 COMMENTS
https://www.arewesafeyet.com
I started writing about cybersecurity in 1993 and 30+ years later we're not any safer. Is it my fault? I don't think so... Maybe. Anyway, today I focus on AI and its quirks, ie. AI security, AI safety, LLM prompt hacking, AI data leaks, adversarial ML, dataset poisoning, AI agents manipulation, you name it.
Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis
Papers

Insights and Current Gaps in Open-Source LLM Vulnerability Scanners: A Comparative Analysis

Luca Sambucci -
0
Cybersecurity Risks of AI-Generated Code (CSET)
Documents

Cybersecurity Risks of AI-Generated Code (CSET)

Luca Sambucci -
0
Medical Hallucinations, hallucinated with Midjourney
Trust issues

Why AI Fantasies don’t belong in your medical file

Luca Sambucci -
0
AI-Robots, imagined by L. Sambucci with Midjourney
Trust issues

AI Robots Are More Hackable Than Your Wi-Fi

Luca Sambucci -
0
Broken AI Mirror, imagined by L. Sambucci with Midjourney
Trust issues

Grounding AI’s flights of fancy: can we stop hallucinations?

Luca Sambucci -
0
Fake Memories, imagined by L. Sambucci with Midjourney
Trust issues

Fake memories, persistent threats: When AI remembers what isn’t true

Luca Sambucci -
0
Achille's heel, imagined by L. Sambucci with Midjourney
Trust issues

LLM’s New Achilles Heel: When Prompts Become Exploits

Luca Sambucci -
0
Not My Mom, imagined by L. Sambucci with Midjourney
Trust issues

Google’s AI Image Flagging: Another Drop in the Ocean

Luca Sambucci -
0
123Page 3 of 3