A Survey on Transferability of Adversarial Examples across Deep Neural Networks

arXiv:2310.17626v2 Announce Type: replace
Abstract: The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has also brought to light a concerning vulnerability: adversarial examples. These crafted inputs, imperceptible to humans, can manipulate machine learning models into making erroneous predictions, raising concerns for safety-critical applications. An intriguing property of this phenomenon is the transferability of adversarial examples, where perturbations crafted …

abstract adversarial adversarial examples arxiv cs.cv domains emergence enabling examples however image image recognition inputs language language processing light natural natural language natural language processing networks neural networks problem-solving processing progress recognition resolution scientific survey tasks type vulnerability