Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape
This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated. Through a novel evaluation approach leveraging clustering for efficient assessment of explanation robustness, we demonstrate that enhancing explanation robustness does not necessarily flatten the input loss landscape with respect to explanation loss - contrary to flattened loss landscapes indicating better classification robustness. To deeply investigate this contradiction, a groundbreaking training method designed to adjust the loss landscape with respect to explanation loss is proposed. Through the new training method, we uncover that although such adjustments can impact the robustness of explanations, they do not have an influence on the robustness of classification. These findings not only challenge the prevailing assumption of a strong correlation between the two forms of robustness but also pave new pathways for understanding relationship between loss landscape and explanation loss.
Code (0)
등록된 구현이 없습니다.
Tasks
Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Do Gradient-based Explanations Tell Anything About Adversarial Robustness to Android Malware?
While machine-learning algorithms have demonstrated a strong ability in detecting Android malware, they can be evaded by sparse evasion attacks crafted by injecting a small set of fake components, e.g., permissions and s…
Adversarial RobustnessAndroid Malware DetectionMalware DetectionAdversarial Examples Are Not Real Features
The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing th…
Contrastive LearningSelf-Supervised LearningTowards unlocking the mystery of adversarial fragility of neural networks
In this paper, we study the adversarial robustness of deep neural networks for classification tasks. We look at the smallest magnitude of possible additive perturbations that can change the output of a classification alg…
Adversarial RobustnessClassificationFeature CompressionExposing Vulnerabilities in Explanation for Time Series Classifiers via Dual-Target Attacks
Interpretable time series deep learning systems are often assessed by checking temporal consistency on explanations, implicitly treating this as evidence of robustness. We show that this assumption can fail: Predictions …
Towards Faithful Explanations for Text Classification with Robustness Improvement and Explanation Guided Training
Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI. However, recent works show that explan…
text-classificationText Classification