SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1912.08166 · 2019

APRICOT: A Dataset of Physical Adversarial Attacks on Object 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

Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset. We present APRICOT, a collection of over 1,000 annotated photographs of printed adversarial patches in public locations. The patches target several object categories for three COCO-trained detection models, and the photos represent natural variation in position, distance, lighting conditions, and viewing angle. Our analysis suggests that maintaining adversarial robustness in uncontrolled settings is highly challenging, but it is still possible to produce targeted detections under white-box and sometimes black-box settings. We establish baselines for defending against adversarial patches through several methods, including a detector supervised with synthetic data and unsupervised methods such as kernel density estimation, Bayesian uncertainty, and reconstruction error. Our results suggest that adversarial patches can be effectively flagged, both in a high-knowledge, attack-specific scenario, and in an unsupervised setting where patches are detected as anomalies in natural images. This dataset and the described experiments provide a benchmark for future research on the effectiveness of and defenses against physical adversarial objects in the wild.

For agents

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

get_harvested_code_for_paper("1912.08166")
get_code_for_paper("1912.08166")
have("1912.08166")

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

curl https://syntology.ai/api/ran/1912.08166.json

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

[![Syntology run record](https://syntology.ai/api/ran/1912.08166.svg)](https://syntology.ai/paper/1912.08166)

Connect an agent — have() is free.