conftrace_

2022 AAAI AAAI 2022

Manipulating SHAP via Adversarial Data Perturbations (Student Abstract)

Abstract

Abstract We introduce a model-agnostic algorithm for manipulating SHapley Additive exPlanations (SHAP) with perturbation of tabular data. It is evaluated on predictive tasks from healthcare and financial domains to illustrate how crucial is the context of data distribution in interpreting machine learning models. Our method supports checking the stability of the explanations used by various stakeholders apparent in the domain of responsible AI; moreover, the result highlights the explanations' vulnerability that can be exploited by an adversary.

🐣 Hot Topic Early Bird - responsible ai

Authors

Hubert Baniecki, Przemyslaw Biecek

Topics

Artificial Intelligence > Core AI > Interpretability Artificial Intelligence > Core AI > Responsible AI Machine Learning > Learning Types > Adversarial Learning Deep Learning > Learning Types > Adversarial Learning Machine Learning > Core Methods > Interpretability

Keywords

adversarial learning responsible ai model interpretability adversarial perturbation model explanation tabular data shap value

More from AAAI 2022

All AAAI 2022 papers →

PESTO: Switching Point Based Dynamic and Relative Positional Encoding for Code-Mixed Languages (Student Abstract)

A Deep Learning-Based Face Mask Detector for Autonomous Nano-Drones (Student Abstract)

Learning Modular Structures That Generalize Out-of-Distribution (Student Abstract)

Multi-Dimension Attention for Multi-Turn Dialog Generation (Student Abstract)

Deep Learning Based Side Channel Attacks on Lightweight Cryptography (Student Abstract)

Annotation Cost-Sensitive Deep Active Learning with Limited Data (Student Abstract)