Who is Responsible for Adversarial Defense?
arXiv:2106.14152
Abstract
We have seen a surge in research aims toward adversarial attacks and defenses in AI/ML systems. While it is crucial to formulate new attack methods and devise novel defense strategies for robustness, it is also imperative to recognize who is responsible for implementing, validating, and justifying the necessity of these defenses. In particular, which components of the system are vulnerable to what type of adversarial attacks, and the expertise needed to realize the severity of adversarial attacks. Also how to evaluate and address the adversarial challenges in order to recommend defense strategies for different applications. This paper opened a discussion on who should examine and implement the adversarial defenses and the reason behind such efforts.
arXiv commentAccepted for poster presentation in ICML 2021 workshop "Challenges in Deploying and monitoring Machine Learning Systems"
References in corpus (18)
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Challenges in Deploying Machine Learning: a Survey of Case Studies
- On Evaluating Adversarial Robustness
- Adversarial Attacks and Defences: A Survey
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
- Defensive Distillation is Not Robust to Adversarial Examples
- NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles
- DPatch: An Adversarial Patch Attack on Object Detectors
- LaVAN: Localized and Visible Adversarial Noise
- MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
- On Adaptive Attacks to Adversarial Example Defenses
- A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
- Adversarial Training Can Hurt Generalization
- On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses
- Detecting and Correcting Adversarial Images Using Image Processing Operations