Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case.
To train a deep neural network to mimic the outcomes of processing sequences, a version of Conditional Generalized Adversarial Network (CGAN) can be used. It has been observed by others that CGAN can help to improve the results even for deterministic sequences, where only one output is associated with the processing of a given input. Surprisingly, our CGAN-based tests on deterministic geophysical processing sequences did not produce a real improvement compared to the use of an $L_p$ loss; we here propose a first theoretical explanation why. Our analysis goes from the non-deterministic case to the deterministic one. It led us to develop an adversarial way to train a content loss that gave better results on our data.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Adversarial training for predictive tasks: theoretical analysis and limitations in the deterministic case
To train a deep neural network to mimic the outcomes of processing sequences, a version of Conditional Generalized Adversarial Network (CGAN) can be used. It has been observed by others that CGAN can help to improve the …
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training examples, which can cause the target DN…
Adversarially Pretrained Transformers may be Universally Robust In-Context Learners
Adversarial training is one of the most effective adversarial defenses, but it incurs a high computational cost. In this study, we show that transformers adversarially pretrained on diverse tasks can serve as robust foun…
In-Context LearningSGD on Neural Networks learns Robust Features before Non-Robust
Neural networks are known to be vulnerable to adversarial attacks - small, imperceptible perturbations that cause the network to misclassify an input. A recent line of work attempts to explain this behavior by positing t…
Designing Adversarially Resilient Classifiers using Resilient Feature Engineering
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by …
Feature EngineeringGeneral Classification