RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

Yan Wang, Bo Yuan, Yi Xie, Huy Phan, Zhuohang Li, Jian Liu, Tianfang Zhang, Cong Shi, Yingying Chen, Tianming Zhao

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 1 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

• huyvnphan/ECCV2022-RIBAC

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

Abstract

Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models. To date, most of the existing studies focus on backdoor attack against the uncompressed model; while the vulnerability of compressed DNNs, which are widely used in the practical applications, is little exploited yet. In this paper, we propose to study and develop Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs, we propose a framework that can learn the proper trigger patterns, model parameters and pruning masks in an efficient way. Thereby achieving high trigger stealthiness, high attack success rate and high model efficiency simultaneously. Extensive evaluations across different datasets, including the test against the state-of-the-art defense mechanisms, demonstrate the high robustness, stealthiness and model efficiency of RIBAC. Code is available at https://github.com/huyvnphan/ECCV2022-RIBAC.

For agents

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

get_harvested_code_for_paper("2208.10608")
get_code_for_paper("2208.10608")
have("2208.10608")

Connect an agent — have() is free.