Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks

Lianli Gao, Shengming Yuan, Yaya Cheng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 12 functions out of this paper's own repositories and ran 10 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

• ylhz/natural-color-fool — marked official in Papers with Code; named in the paper
• ylhz/Natural-Color-Fool

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

Abstract

Unrestricted color attacks, which manipulate semantically meaningful color of an image, have shown their stealthiness and success in fooling both human eyes and deep neural networks. However, current works usually sacrifice the flexibility of the uncontrolled setting to ensure the naturalness of adversarial examples. As a result, the black-box attack performance of these methods is limited. To boost transferability of adversarial examples without damaging image quality, we propose a novel Natural Color Fool (NCF) which is guided by realistic color distributions sampled from a publicly available dataset and optimized by our neighborhood search and initialization reset. By conducting extensive experiments and visualizations, we convincingly demonstrate the effectiveness of our proposed method. Notably, on average, results show that our NCF can outperform state-of-the-art approaches by 15.0%∼32.9% for fooling normally trained models and 10.0%∼25.3% for evading defense methods. Our code is available at https://github.com/ylhz/Natural-Color-Fool.

For agents

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

get_harvested_code_for_paper("2210.02041")
get_code_for_paper("2210.02041")
have("2210.02041")

Connect an agent — have() is free.