Deceptive AI Explanations: Creation and Detection

01/21/2020
by   Johannes Schneider, et al.
0

Artificial intelligence comes with great opportunities and but also great risks. We investigate to what extent deep learning can be used to create and detect deceptive explanations that either aim to lure a human into believing a decision that is not truthful to the model or provide reasoning that is non-faithful to the decision. Our theoretical insights show some limits of deception and detection in the absence of domain knowledge. For empirical evaluation, we focus on text classification. To create deceptive explanations, we alter explanations originating from GradCAM, a state-of-art technique for creating explanations in neural networks. We evaluate the effectiveness of deceptive explanations on 200 participants. Our findings indicate that deceptive explanations can indeed fool humans. Our classifier can detect even seemingly minor attempts of deception with accuracy that exceeds 80% given sufficient domain knowledge encoded in the form of training data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/27/2020

Teaching the Machine to Explain Itself using Domain Knowledge

Machine Learning (ML) has been increasingly used to aid humans to make b...
research
08/23/2021

Knowledge-based XAI through CBR: There is more to explanations than models can tell

The underlying hypothesis of knowledge-based explainable artificial inte...
research
09/18/2023

Evaluation of Human-Understandability of Global Model Explanations using Decision Tree

In explainable artificial intelligence (XAI) research, the predominant f...
research
04/12/2022

Enriching Artificial Intelligence Explanations with Knowledge Fragments

Artificial Intelligence models are increasingly used in manufacturing to...
research
10/22/2019

Digital Twin approach to Clinical DSS with Explainable AI

We propose a digital twin approach to improve healthcare decision suppor...
research
02/20/2020

Do you comply with AI? – Personalized explanations of learning algorithms and their impact on employees' compliance behavior

Machine Learning algorithms are technological key enablers for artificia...
research
12/16/2020

Applying Deutsch's concept of good explanations to artificial intelligence and neuroscience – an initial exploration

Artificial intelligence has made great strides since the deep learning r...

Please sign up or login with your details

Forgot password? Click here to reset