Quantization Aware Attack: Enhancing the Transferability of Adversarial Attacks across Target Models with Different Quantization Bitwidths. (arXiv:2305.05875v1 [cs.CR])

Quantized Neural Networks (QNNs) receive increasing attention in
resource-constrained scenarios because of their excellent generalization
abilities, but their robustness under realistic black-box adversarial attacks
has not been deeply studied, in which the adversary requires to improve the
attack capability across target models with unknown quantization bitwidths. One
major challenge is that adversarial examples transfer poorly against QNNs with
unknown bitwidths because of the quantization shift and gradient misalignment
issues. This paper proposes the Quantization Aware Attack to enhance the attack …

adversarial adversarial attacks adversary attack attacks attention aware box networks neural networks robustness target under