Influence-based Attributions can be Manipulated
Influence Functions are a standard tool for attributing predictions to training data in a principled manner and are widely used in applications such as data valuation and fairness. In this work, we present realistic incentives to manipulate influence-based attributions and investigate whether these attributions can be \textit{systematically} tampered by an adversary. We show that this is indeed possible for logistic regression models trained on ResNet feature embeddings and standard tabular fairness datasets and provide efficient attacks with backward-friendly implementations. Our work raises questions on the reliability of influence-based attributions in adversarial circumstances. Code is available at : \url{https://github.com/infinite-pursuits/influence-based-attributions-can-be-manipulated}
Code (1)
Tasks
Data ValuationFairnessMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation
Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object. AdvCAM is an attribution map of…
Adversarial AttackObjectSegmentationSemantic Segmentation+3Certifiably Robust Interpretation via Renyi Differential Privacy
Motivated by the recent discovery that the interpretation maps of CNNs could easily be manipulated by adversarial attacks against network interpretability, we study the problem of interpretation robustness from a new per…
Computational EfficiencyAnti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization
Obtaining accurate pixel-level localization from class labels is a crucial process in weakly supervised semantic segmentation and object localization. Attribution maps from a trained classifier are widely used to provide…
Adversarial AttackObjectObject LocalizationSemantic Segmentation+4Towards Aggregating Weighted Feature Attributions
Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a trainin…
AttributeMinimizing False-Positive Attributions in Explanations of Non-Linear Models
Suppressor variables can influence model predictions without being dependent on the target outcome and they pose a significant challenge for Explainable AI (XAI) methods. These variables may cause false-positive feature …
Hyperparameter Optimization