A Survey On Universal Adversarial Attack
By Chaoning Zhang, Philipp Benz, Chenguo Lin, Adil Karjauv, Jing Wu, In-So Kweon. 2021
115 citations recorded by the source corpus.
The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of universal adversarial perturbations (UAPs), i.e. a single perturbation to fool the target DNN for most images. With the focus on UAP against deep classifiers, this survey summarizes the recent progress on universal adversarial attacks, discussing the challenges from both the attack and defense sides, as well as the reason for the existence of UAP. We aim to extend this work as a dynamic survey that will regularly update its content to follow new works regarding UAP or universal attack in a wide range of domains, such as image, audio, video, text, etc. Relevant updates will be discussed at: https://bit.ly/2SbQlLG. We welcome authors of future works in this field to contact us for including your new findings.
Subfields: Artificial Intelligence, Molecular Biology, Safety, Robustness & Interpretability
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
- Iason Gabriel
- Po-Sen Huang
- Jonathan Uesato
- Deyi Xiong
- William S. Isaac
- John F. J. Mellor
- Borja Balle
- Xinwei Wu
In Molecular Biology
In Safety, Robustness & Interpretability
- Iason Gabriel
- Po-Sen Huang
- William S. Isaac
- John F. J. Mellor
- Borja Balle
- Xinwei Wu
- Tianhao Shen
- Geoffrey Irving
Citations in the corpus
- Ethical and social risks of harm from Language Models (2021, background): “…et al. (2019); Krittanawong et al. (2020); Wang et al. (2019b) Branwen (2020); Dale (2021); Lacker (2020); Lin et al. (2021); Rae et al. (2021); Zhang et al. (2021b) 2.3.3 Causing material harm by disseminating misinformation e.g. in medicine or law Quach (2020) 2.3.4 Leading users to perform…”
- Large Language Model Alignment: A Survey (2023, background): “On the other hand, LLMs can be used for illegal purposes, such as generating codes for cyber attacks (Zhang et al., 2021; Chen et al., 2021a), or even creating lethal weapons (Sandbrink, 2023).”