Portal de Periódicos da CAPES

Effective Universal Unrestricted Adversarial Attacks Using a MOE Approach

2021; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-3-030-72699-7_35

1611-3349

Alina Elena Baia, Gabriele Di Bari, Valentina Poggioni,

Physical Unclonable Functions (PUFs) and Hardware Security

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested evolutionary algorithm to generate universal unrestricted adversarial examples in a black-box scenario. The unrestricted attacks are performed through the application of well-known image filters that are available in several image processing libraries, modern cameras, and mobile applications. The multi-objective optimization takes into account not only the attack success rate but also the detection rate. Experimental results showed that this approach is able to create a sequence of filters capable of generating very effective and undetectable attacks.