A Vulnerability of Attribution Methods Using Pre-Softmax Scores
We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is known that this type of networks are vulnerable to adversarial attacks, in which imperceptible perturbations of the input may alter the outputs of the model. In contrast, here we focus on effects that small modifications in the model may cause on the attribution method without altering the model outputs.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?
Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of pre-softmax scores versus post-softmax s…
A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs
We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of a…
On Attribution of Recurrent Neural Network Predictions via Additive Decomposition
RNN models have achieved the state-of-the-art performance in a wide range of text mining tasks. However, these models are often regarded as black-boxes and are criticized due to the lack of interpretability. In this pape…
Decision MakingImproving Adversarial Robustness of Attribution via Implicit Regularization
The adversarial robustness of attributions is a fundamental requirement for reliable explainability in deep learning, yet existing approaches typically rely on computationally expensive explicit regularization. In this w…
Adversarial RobustnessSHIELD: Thwarting Code Authorship Attribution
Authorship attribution has become increasingly accurate, posing a serious privacy risk for programmers who wish to remain anonymous. In this paper, we introduce SHIELD to examine the robustness of different code authorsh…
Authorship Attribution