SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.07012 · 2022

Adversarial vulnerability of powerful near out-of-distribution detection

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

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

Abstract

There has been a significant progress in detecting out-of-distribution (OOD) inputs in neural networks recently, primarily due to the use of large models pretrained on large datasets, and an emerging use of multi-modality. We show a severe adversarial vulnerability of even the strongest current OOD detection techniques. With a small, targeted perturbation to the input pixels, we can change the image assignment from an in-distribution to an out-distribution, and vice versa, easily. In particular, we demonstrate severe adversarial vulnerability on the challenging near OOD CIFAR-100 vs CIFAR-10 task, as well as on the far OOD CIFAR-100 vs SVHN. We study the adversarial robustness of several post-processing techniques, including the simple baseline of Maximum of Softmax Probabilities (MSP), the Mahalanobis distance, and the newly proposed \textit{Relative} Mahalanobis distance. By comparing the loss of OOD detection performance at various perturbation strengths, we demonstrate the beneficial effect of using ensembles of OOD detectors, and the use of the \textit{Relative} Mahalanobis distance over other post-processing methods. In addition, we show that even strong zero-shot OOD detection using CLIP and multi-modality suffers from a severe lack of adversarial robustness as well. Our code is available at https://github.com/stanislavfort/adversaries_to_OOD_detection

For agents

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

get_harvested_code_for_paper("2201.07012")
get_code_for_paper("2201.07012")
have("2201.07012")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2201.07012.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2201.07012.svg)](https://syntology.ai/paper/2201.07012)

Connect an agent — have() is free.