y0news
← Feed
Back to feed
🧠 AI NeutralImportance 6/10

Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?

arXiv – CS AI|Anna Chistyakova, Mikhail Pautov|
🤖AI Summary

Researchers propose Contract And Conquer (CAC), a new method for provably generating adversarial examples against black-box neural networks using knowledge distillation and search space contraction. The approach provides theoretical guarantees for finding adversarial examples within a fixed number of iterations and outperforms existing methods on ImageNet datasets including vision transformers.

Key Takeaways
  • CAC introduces the first provable method for generating adversarial examples in black-box settings with transferability guarantees.
  • The method combines knowledge distillation on expanding datasets with precise contraction of adversarial search spaces.
  • Experimental results show superior performance compared to state-of-the-art black-box attack methods on ImageNet.
  • The approach successfully targets modern architectures including vision transformers.
  • The research addresses a key limitation in existing adversarial attack methods that lack theoretical guarantees.
Read Original →via arXiv – CS AI
Act on this with AI
Stay ahead of the market.
Connect your wallet to an AI agent. It reads balances, proposes swaps and bridges across 15 chains — you keep full control of your keys.
Connect Wallet to AI →How it works
Related Articles