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

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.

• →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.