My adversarial prompt detector was flagging academic papers as GCG suffix attacks. Not occasionally....
My adversarial prompt detector was flagging academic papers as GCG suffix attacks.
Not occasionally. 72% of the time.
Here's what happened, why it makes complete sense in hindsight, and the fix that brought it down to 6.7%.
What GCG Suffix Attacks Look Like
GCG (Greedy Coordinate Gradient) attacks are adversarial strings that look like complete noise:
Two weeks ago, a Windows trojan slipped into my MCP (Model Context Protocol) marketplace. The malware...
Everyone's worried about prompt injection making models say bad things. Meanwhile someone piped LLM...
I found this out the embarrassing way by " _attacking my own system _". I maintain FIE, an...
The Problem With the rise of ChatGPT and enterprise LLM integrations, a new attack vector...
This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the…
I spent the last while building a prompt-injection detector trained on 78,000+ attack samples. Here's...
