Adversarial Attacks and Defenses in Deep Learning

By Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu. Engineering, 2020

650 citations recorded by the source corpus.

Abstract With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques, it is critical to ensure the security and robustness of the deployed algorithms. Recently, the security vulnerability of DL algorithms to adversarial samples has been widely recognized. The fabricated samples can lead to various misbehaviors of the DL models while being perceived as benign by humans. Successful implementations of adversarial attacks in real physical-world scenarios further demonstrate their practicality. Hence, adversarial attack and defense techniques have attracted increasing attention from both machine learning and security communities and have become a hot research topic in recent years. In this paper, we first introduce the theoretical foundations, algorithms, and applications of adversarial attack techniques. We then describe a few research efforts on the defense techniques, which cover the broad frontier in the field. Several open problems and challenges are subsequently discussed, which we hope will provoke further research efforts in this critical area.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/fbf32abd431c70293f1ad1a9b85d4ecbe4e5d6ed

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Hongzhi Yin

Citations in the corpus

Security and Privacy for 6G: A Survey on Prospective Technologies and Challenges (2021, methodology): “Figure 24 illustrates a simple defense method against the algorithm poisoning attack from the study [228], where the adversarial model can be detected by comparing the model predictions on the original and squeezed data inputs.”
Sensor and Sensor Fusion Technology in Autonomous Vehicles: A Review (2021, background): “A detailed discussion about the sensor fusion challenges, including adversarial attacks and possible preventions is beyond the scope of this paper (see [16,202,205-209] for a more comprehensive overview).”
Security and Privacy Challenges of Large Language Models: A Survey (2024, positive): “In the deep neural networks (DNNs) context, an adversarial attack involves manipulating input data to cause the network to produce incorrect or unintended outputs [80].”
A Survey of Machine Unlearning (2022, positive): “Recently, deep learning models have been shown to be vulnerable to external attacks, especially adversarial attacks [121].”