Towards Verifying the Geometric Robustness of Large-Scale Neural Networks

Xiaowei Huang, Wenjie Ruan, Fu Wang, Peipei Xu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• TrustAI/GeoRobust

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation. This paper aims to verify the robustness of large-scale DNNs against the combination of multiple geometric transformations with a provable guarantee. Given a set of transformations (e.g., rotation, scaling, etc.), we develop GeoRobust, a black-box robustness analyser built upon a novel global optimisation strategy, for locating the worst-case combination of transformations that affect and even alter a network's output. GeoRobust can provide provable guarantees on finding the worstcase combination based on recent advances in Lipschitzian theory. Due to its black-box nature, GeoRobust can be deployed on large-scale DNNs regardless of their architectures, activation functions, and the number of neurons. In practice, GeoRobust can locate the worst-case geometric transformation with high precision for the ResNet50 model on Ima-geNet in a few seconds on average. We examined 18 Im-ageNet classifiers, including the ResNet family and vision transformers, and found a positive correlation between the geometric robustness of the networks and the parameter numbers. We also observe that increasing the depth of DNN is more beneficial than increasing its width in terms of improving its geometric robustness. Our tool GeoRobust is available at https://github.com/TrustAI/GeoRobust.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.12456")
get_code_for_paper("2301.12456")
have("2301.12456")

Connect an agent — have() is free.