A bidirectional domain separation adversarial network based transfer learning method for near-infrared spectra
3
Citation
73
Reference
10
Related Paper
Citation Trend
Keywords:
Transfer of learning
Source Separation
Separation (statistics)
Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models intrinsically. During the last few years, adversarial training has been studied and discussed from various aspects. A variety of improvements and developments of adversarial training are proposed, which were, however, neglected in existing surveys. For the first time in this survey, we systematically review the recent progress on adversarial training for adversarial robustness with a novel taxonomy. Then we discuss the generalization problems in adversarial training from three perspectives. Finally, we highlight the challenges which are not fully tackled and present potential future directions.
Robustness
Training set
Cite
Citations (12)
This chapter begins with a comparison of the inquisitorial and adversarial systems of criminal procedure. It then discusses trial proceedings; appellate proceedings; and the adoption of the adversarial model at the international level.
Cite
Citations (0)
Blind separation techniques of sound sources, designed to work with voice signals, present a performance highly dependent on the number of coefficients of the separation system. In general, different environments require different lengths of separation filters. This paper proposes the use of reverberation time information arising from lateral blind estimation techniques for tuning the degree of freedom of the separation system in order to blindly obtain a reasonable source-to-distortion ratio (SDR). This tuning enables, for example, that the complexity of the separation system be adjusted in each band if a subband structure is employed for sources separation.
Separation (statistics)
Source Separation
Distortion (music)
Separation method
Cite
Citations (0)
Realization (probability)
Cite
Citations (2)
Cite
Citations (0)
The adversarial system of litigation assumes that parties are able to present their disputes before an impartial tribunal, by use of professional legal advocates. This work critiques some of the fundamental assumptions of the adversarial system and examines two case studies in which it has failed to deliver justice for litigants.
Cite
Citations (0)
Abstract This chapter examines the criticisms and reforms that might be applied to adversarial experts. It presents several criticisms of adversary expertise. It agrees with Wigmore in saying that cross-examination is the greatest legal engine ever invented for the discovery of truth. It also enumerates several negative points of cross-examination, as well as bias and adversarial system.
Cross-examination
Cite
Citations (0)
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are more vulnerable to adversarial attacks; and (2) successful adversarial attacks lead to deviated and scattered activation map. Therefore, we use the mask method to design an attention-preserving loss and a contrast method to design a loss that makes the model’s attention rectification. Accordingly, an attention-based adversarial defense framework is designed, under which better adversarial training or stronger adversarial attacks can be performed through the above constraints. We hope the attention-related data analysis and defense solution in this study will shed some light on the mechanism behind the adversarial attack and also facilitate future adversarial defense/attack model design.
Cite
Citations (3)
Adversarial training is one of the most effective approaches for deep learning models to defend against adversarial examples. Unlike other defense strategies, adversarial training aims to enhance the robustness of models intrinsically. During the past few years, adversarial training has been studied and discussed from various aspects, which deserves a comprehensive review. For the first time in this survey, we systematically review the recent progress on adversarial training for adversarial robustness with a novel taxonomy. Then we discuss the generalization problems in adversarial training from three perspectives and highlight the challenges which are not fully tackled. Finally, we present potential future directions.
Robustness
Training set
Cite
Citations (286)