Work

Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research Directions

Year: 2024

Type: article

Abstract: Deep neural network (DNN) classifiers are potent instruments that can be used in various security-sensitive applications. Nonetheless, they are vulnerable to certain attacks that impede or distort their learning process. For example, backdoor attacks involve polluting the DNN learning set with a few samples from one or more source classes, which are then labelled as a target class set by an attacker. Even if the DNN is trained on clean samples with no backdoors, this attack will still be successful if a backdoor pattern exists in the training data. Backdoor attacks are difficult to spot and can be used to make the DNN behave maliciously depending on the target selected by the attacker. In this study, we survey the literature and highlight the latest advances in backdoor attack strategies and defense mechanisms. We finalize the discussion on challenges and open issues, as well as future research opportunities.

Source: IEEE Access

DOI: 10.1109/access.2024.3355816

Authors: Orson Mengara, Anderson Avila, Tiago H. Falk

Institutions: Université du Québec à Montréal, Institut National de la Recherche Scientifique, Université du Québec en Outaouais

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,995

OpenAlex ID: W4390969331