quiz bu lëkkale ak tegtal · Dëgër Niveau

Quiz ci modelu diffusion

Dafay saytu li memorisation ci xeetu diffusion yi di tekki, lu tax done yu ñaar yuñ tàggat ñoo ko waral, ak ni gëstukat yi di génne ak wàññi ay kopi yu jege.

Yooni njiit yu jëm ciMemorisation ci modelu diffusion
Laaj 1 de 8

Luy xam-xam ci xeetu diffusion?

Xoolaatal laaj bu nekk8 laaj

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

  1. Luy xam-xam ci xeetu diffusion?
    • The model remembering a user's previous prompts
    • The model reproducing specific training images almost exactly
    • The model storing images in a database for search
    • The model forgetting how to draw after training
  2. Lan moo waral done yuñ ñaareel di yokk mën mën?
    • Duplicates are stored in higher resolution
    • Duplicates are removed automatically before training
    • When an image appears many times, storing it becomes the easiest way to reduce training loss on it
    • Duplicates confuse the model so it outputs noise
  3. Lan la Carlini ak ay naataangoom wane ci këyitu 2023 bi?
    • Diffusion models never copy training data
    • Only text models memorize data
    • Memorization only happens in black and white images
    • Over a hundred near-identical training images could be extracted from Stable Diffusion
  4. naka la ko extraction attaque bi di xàmmee nataal yuñ mëna jàpp ci bopp?
    • It looked for near-identical generations across many seeds for the same caption
    • It read the model's weights directly as images
    • It asked the model which images it had memorized
    • It searched the web for similar photos
  5. Ban wax ci lu jëm ci jàng ci xel moo dëggu?
    • It is the model's normal behavior for every prompt
    • It is rare but can be targeted by a determined user
    • It only occurs as exact pixel copies
    • It has no relevance to privacy
  6. Why is privacy risk sharper when fine-tuning on a small dataset such as medical scans?
    • Small datasets are always public
    • Medical scans are too large to train on
    • Each example has more influence on the model, raising the chance of regurgitation
    • Fine-tuning deletes the base model
  7. Which mitigation bounds the influence of any single training example but currently reduces image quality?
    • Differentially private training
    • Increasing the number of sampling steps
    • Using longer prompts
    • Training for more epochs
  8. Why is deduplication more effective when it removes near-duplicates, not only exact copies?
    • Exact copies do not affect training
    • Near-duplicates are illegal to store
    • Near-duplicates make images blurrier
    • Slightly edited versions of the same image still act as repeated exposure