University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Adversarial Explanations - You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

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

Download to your calendar using vCal

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:

Note that ex-directory lists are not shown.

Other lists

SS28 (Common Room) Museum of Archaeology & Anthropology Department of Earth Sciences

Other talks

Title to be confirmed There is no such thing as weather: a historical and cultural geography of weather (and health) Secrets of the Surface: The Mathematical Vision of Maryam Mirzakhani ( EDI Film Screening) "That's History. That's Truth. I Seen It Myself": T'tc~tsa (Wailaki) and the Enslavement of California Native Americans. Ice in a mostly-Arctic Context Machine Learning for Spectral Geometry and Vice Versa
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity