The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability

Stephen Casper, Jieun Yun, Joonhyuk Baek, Yeseong Jung, Minhwan Kim +11 more
4/3/2024
cs.LGcs.AI

No official code found. Best implementation: cmu-sei/feud (9 stars, last commit 2024-04-09).

Abstract

Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying convolutional neural networks (CNNs) at the ImageNet scale. The objective of the competition was to help human crowd-workers identify trojans in CNNs. This report showcases the methods and results of four featured competition entries. It remains challenging to help humans reliably diagnose trojans via interpretability tools. However, the competition's entries have contributed new techniques and set a new record on the benchmark from Casper et al., 2023.

View on arXivView PDF

Code Implementations(1)

cmu-sei/feudCommunity100%

AI Division, Reverse Engineering CNN Trojans

91PythonMar 19, 20242 years agoNOASSERTION
artificial-intelligencecomputer-visoninterpretabilityinterpretable-aireverse-engineering

Cite this paper

@article{casper2024satml,
  title  = {The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability},
  author = {Stephen Casper and Jieun Yun and Joonhyuk Baek and Yeseong Jung and Minhwan Kim and Kiwan Kwon and Saerom Park and Hayden Moore and David Shriver and Marissa Connor and Keltin Grimes and Angus Nicolson and Arush Tagade and Jessica Rumbelow and Hieu Minh Nguyen and Dylan Hadfield-Menell},
  year   = {2024},
  eprint = {2404.02949},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.02949v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.02949.svg)](https://codeofpaper.com/paper/2404.02949)

Discussion