Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks
نویسندگان
چکیده
منابع مشابه
Defending Non-Bayesian Learning against Adversarial Attacks
Abstract This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state. We focus on the impact of the adversarial agents on the performance of consensus-based non-Bayesian learning, where non-faulty agents combine local le...
متن کاملTowards Imperceptible and Robust Adversarial Example Attacks against Neural Networks
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbations to the input. Previous adversarial example crafting methods, however, use s...
متن کاملAdversarial Attacks on Image Recognition
The purpose of this project is to extend the work done by Papernot et al. in [4] on adversarial attacks in image recognition. We investigated whether a reduction in feature dimensionality can maintain a comparable level of misclassification success while increasing computational efficiency. We formed an attack on a black-box model with an unknown training set by forcing the oracle to misclassif...
متن کاملMagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examples
MagNet and “Efficient Defenses...” were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.
متن کاملRobust Deep Reinforcement Learning with Adversarial Attacks
This paper proposes adversarial attacks for Reinforcement Learning (RL) and then improves the robustness of Deep Reinforcement Learning algorithms (DRL) to parameter uncertainties with the help of these attacks. We show that even a naively engineered attack successfully degrades the performance of DRL algorithm. We further improve the attack using gradient information of an engineered loss func...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33018417