Rearchitecting Classification Frameworks For Increased Robustness
원문 초록
While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the real world. These defenses also come at a cost to accuracy. Fortunately, there are invariances of an object that are its salient features; when we break them it will necessarily change the perception of the object. We find that applying invariants to the classification task makes robustness and accuracy feasible together. Two questions follow: how to extract and model these invariances? and how to design a classification paradigm that leverages these invariances to improve the robustness accuracy trade-off? The remainder of the paper discusses solutions to the aformenetioned questions.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Safeguarding Federated Learning-based Road Condition Classification
DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic
Low-Density 3D Point Cloud Classification
POINTVIEW-GCN: 3D SHAPE CLASSIFICATION WITH MULTI-VIEW POINT CLOUDS
Generative Adversarial Minority Oversampling for Spectral-Spatial Hyperspectral Image Classification
Attention-Based Adaptive Spectral-Spatial Kernel ResNet for Hyperspectral Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.