Kuiz berkaitan panduan · Sederhana Tahap

Bias Bounties and Algorithmic Bug Bounties Quiz

Covers Twitter’s bounded 2021 crop-model challenge, bounty design, reproducibility, incentives and limits as a voluntary audit method.

Laluan panduan yang berkaitanBias Bounties And Algorithmic Bug Bounties
soalan 1 daripada 8

Model apakah yang disasarkan oleh cabaran bounty bias algoritma Twitter 2021?

Pratonton setiap soalan8 soalan

Jawapan dan penjelasan muncul semasa anda mengambil kuiz.

  1. Model apakah yang disasarkan oleh cabaran bounty bias algoritma Twitter 2021?
    • Every post recommendation system on Twitter
    • Its image saliency and automatic-cropping model
    • A facial-recognition system
    • A bank credit model
  2. Apakah akses yang diterima oleh peserta untuk cabaran yang diumumkan?
    • A public demo API that returned example crops without exposing the model.
    • Generated image examples and evaluation labels without access to the generation code.
    • The saliency model and crop-generation code
    • A small set of saliency scores without the crop-generation code.
  3. Mengapakah ganjaran berat sebelah tidak bersamaan dengan ganjaran kelemahan keselamatan?
    • Security reports never need evidence
    • A bias bounty is always a software exploit test
    • A bias bounty automatically changes the law
    • Potential social harms need context, affected-population evidence and choices about fairness criteria
  4. Jika tiada penyelidik melaporkan berat sebelah semasa pemberian hadiah, apakah had yang kekal?
    • It certifies legal compliance
    • It proves every group is treated equally
    • It shows no one used the system
    • The result does not prove the model is free of bias or harm
  5. Butiran manakah yang menjadikan penemuan berat sebelah yang diserahkan lebih boleh dihasilkan semula?
    • A conclusion without test data
    • A screenshot with no context
    • Model version, test population, metric, comparison and limitations
    • A list of protected groups only
  6. Why might a prize contest overrepresent easy-to-demonstrate harms?
    • Time, access and prize criteria can favor findings that are easy to test over less visible harms
    • Awards eliminate all conflicts of interest
    • Every harm is equally measurable
    • A model’s training data is always public
  7. Which practice helps protect affected people and good-faith researchers?
    • Encourage participants to scrape private accounts
    • Clear authorized scope, privacy safeguards, confidential disclosure and a response process
    • Publish raw sensitive data with each report
    • Make acceptance depend only on publicity
  8. How should an organization interpret a successful bias bounty?
    • As bounded evidence for risk management, not a fairness certificate
    • As a replacement for appeals and internal testing
    • As proof that all company models are unbiased
    • As legal approval from regulators