paper-with-me

Papers

Influence-based Attributions can be Manipulated

2024-09-08 · Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri

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}

📄 PDF Abstract BibTeX arXiv:2409.05208

Code (1)

infinite-pursuits/influence-based-attributions-can-be-manipulated 공식 구현

Tasks

Data ValuationFairness

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Kaiming Initialization 설명 없음
Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

2021-03-16 · CVPR 2021 1 · Jungbeom Lee, Eunji Kim, Sungroh Yoon

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+3

Certifiably Robust Interpretation via Renyi Differential Privacy

2021-07-04 · Ao Liu, Xiaoyu Chen, Sijia Liu, Lirong Xia 외

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 Efficiency

Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

2022-04-11 · Jungbeom Lee, Eunji Kim, Jisoo Mok, Sungroh Yoon

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+4

Towards Aggregating Weighted Feature Attributions

2019-01-20 · Umang Bhatt, Pradeep Ravikumar, Jose M. F. Moura

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…

Attribute

Minimizing False-Positive Attributions in Explanations of Non-Linear Models

2025-05-16 · Anders Gjølbye, Stefan Haufe, Lars Kai Hansen

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