Understanding Black-box Predictions via Influence Functions

Pang Wei Koh, Percy Liang

Type: Preprint

Publication Date: 2017-01-01

Citations: 1137

DOI: https://doi.org/10.48550/arxiv.1703.04730

View Publication

Locations

arXiv (Cornell University) - View
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Understanding Black-box Predictions via Influence Functions	2017	Pang Wei Koh Percy Liang
+	Deeper Understanding of Black-box Predictions via Generalized Influence Functions	2023	Hyeonsu Lyu Jonggyu Jang Se-Hyun Ryu Hyun Jong Yang
+	How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection	2022	Mantas Mazeika Bo Li David Forsyth
+	Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning	2020	Luiz F. O. Chamon Santiago Paternain Alejandro Ribeiro
+	Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning.	2020	Luiz F. O. Chamon Santiago Paternain Alejandro Ribeiro
+	Theoretical and Practical Perspectives on what Influence Functions Do	2023	Andrea Schioppa Katja Filippova Ivan Titov Polina Zablotskaia
+ PDF Chat	The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes	2024	Myeongseob Ko Feiyang Kang Weiyan Shi Ming Jin Yu Zhou Ruoxi Jia
+	Training Data Influence Analysis and Estimation: A Survey	2022	Zayd Hammoudeh Daniel Lowd
+	FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging	2020	Han Guo Nazneen Fatema Rajani Peter Hase Mohit Bansal Caiming Xiong
+	Estimating Training Data Influence by Tracing Gradient Descent	2020	Garima Pruthi Frederick Liu Mukund Sundararajan Satyen Kale
+	Estimating Training Data Influence by Tracking Gradient Descent	2020	Garima Pruthi Frederick Liu Mukund Sundararajan Satyen Kale
+	Influence Functions in Deep Learning Are Fragile	2020	Samyadeep Basu Phil Pope Soheil Feizi
+	Influence Functions in Deep Learning Are Fragile	2020	Samyadeep Basu Philip Pope Soheil Feizi
+ PDF Chat	FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging	2021	Han Guo Nazneen Fatema Rajani Peter Hase Mohit Bansal Caiming Xiong
+	Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives	2023	Haoyang Liu Maheep Chaudhary Haohan Wang
+	Revisiting the Fragility of Influence Functions	2023	Jacob R. Epifano Ravi P. Ramachandran Aaron J. Masino Ghulam Rasool
+	Theoretical Foundations of Adversarially Robust Learning	2023	Omar Montasser
+	Trustworthy Machine Learning	2023	Bálint Mucsányi Michael Kirchhof Elisa Nguyen Alexander Rubinstein Seung‐June Oh
+	Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples	2021	Maura Pintor Luca Demetrio Angelo Sotgiu Ambra Demontis Nicholas Carlini Battista Biggio Fabio Roli
+ PDF Chat	BadGD: A unified data-centric framework to identify gradient descent vulnerabilities	2024	Chi‐Hua Wang Guang Cheng

Works That Cite This (731)

Action	Title	Year	Authors
+	Explaining Latent Representations with a Corpus of Examples	2021	Jonathan Crabbé Zhaozhi Qian Fergus Imrie Mihaela van der Schaar
+	Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay	2021	Fan Zhou Chengtai Cao
+ PDF Chat	Towards Adversarial Malware Detection	2019	Davide Maiorca Battista Biggio Giorgio Giacinto
+ PDF Chat	The Threat of Offensive AI to Organizations	2022	Yisroel Mirsky Ambra Demontis Jaidip Kotak Ram Shankar Gelei Deng Yang Liu Xiangyu Zhang Maura Pintor Wenke Lee Yuval Elovici
+ PDF Chat	Towards a mathematical framework to inform neural network modelling via polynomial regression	2021	Pablo Morala Jenny Cifuentes Rosa E. Lillo Iñaki Ucar
+	Fairness Under Feature Exemptions: Counterfactual and Observational Measures	2021	Sanghamitra Dutta Praveen Venkatesh Piotr Mardziel Anupam Datta Pulkit Grover
+	Causal Interpretability for Machine Learning -- Problems, Methods and Evaluation	2020	Raha Moraffah Mansooreh Karami Ruocheng Guo Adrienne Raglin Huan Liu
+	Evaluating the Correctness of Explainable AI Algorithms for Classification	2021	Orcun Yalcin Xiuyi Fan Siyuan Liu
+ PDF Chat	An explainable deep vision system for animal classification and detection in trail-camera images with automatic post-deployment retraining	2021	Golnaz Moallem Don Pathirage Joel Reznick James F. Gallagher Hamed Sari‐Sarraf
+	Efficient Data-Dependent Learnability.	2020	Yaniv Fogel Tal Shapira Meir Feder

Works Cited by This (19)

Action	Title	Year	Authors
+ PDF Chat	Influential Observations, High Leverage Points, and Outliers in Linear Regression	1986	Samprit Chatterjee Ali S. Hadi
+	Characterizations of an Empirical Influence Function for Detecting Influential Cases in Regression	1980	R. Dennis Cook Sanford Weisberg
+	Detection of Influential Observation in Linear Regression	2000	R. Dennis Cook
+	Assessing Influence on Predictions from Generalized Linear Models	1990	William Thomas R. Dennis Cook
+ PDF Chat	On the limited memory BFGS method for large scale optimization	1989	Cheng‐Di Dong Jorge Nocedal
+	Assessment of Local Influence	1986	R. Dennis Cook
+ PDF Chat	ImageNet Large Scale Visual Recognition Challenge	2015	Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael S. Bernstein
+	On Robustness Properties of Convex Risk Minimization Methods for Pattern Recognition	2004	Andreas Christmann Ingo Steinwart
+ PDF Chat	Residuals and Influence in Regression	1984	Robert F. Ling R. Dennis Cook Sanford Weisberg
+	Generalized Leverage and its Applications	1998	Bo‐Cheng Wei Yue‐Qing Hu Wing–Kam Fung