How to Backdoor an AI Model: For Dummies

Sophie Kim

Apr 7

in which I explain LLMs, LoRA, and how me and Claude backdoored an AI model in a day

Read →

4 Comments

Austin Morrissey

Apr 14Edited

i love the photo in this

another banger

🫶🫶🫶

How does the matrix starting at 0 mean that the weights have no impact?

I thought the underlying operation was matrix multiplication, so 0 would zero out the weights

Reply

Share

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts

The Counterfactual

How to Backdoor an AI Model: For Dummies