Adversarial Explanations - You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods

Add to your list(s) Download to your calendar using vCal

• Botty Dimanov (University of Cambridge)
• Tuesday 09 June 2020, 13:15-14:15
• Online on Teams.

If you have a question about this talk, please contact Mateja Jamnik.

ONLINE link.

Transparency of algorithmic systems has been discussed as a way for end-users and regulators to develop appropriate trust in machine learning models. One popular approach, LIME (Ribeiro et al 2016) even suggests that model explanations can answer the question ``Why should I trust you?’’ Here we show a straightforward method for modifying a pre-trained model to manipulate the output of many popular feature importance explanation methods with little change in accuracy, thus demonstrating the danger of trusting such explanation methods. We show how this explanation attack can mask a model’s discriminatory use of a sensitive feature, raising strong concerns about using such explanation methods to check model fairness.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Artificial Intelligence Research Group Talks (Computer Laboratory)
• Chris Davis' list
• Computer Laboratory talks
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• Online on Teams
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• yk373's list

Note that ex-directory lists are not shown.