A Proxy-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks

by   Ziqiang Li, et al.
Huazhong University of Science u0026 Technology

Poisoning efficiency is a crucial factor in poisoning-based backdoor attacks. Attackers prefer to use as few poisoned samples as possible to achieve the same level of attack strength, in order to remain undetected. Efficient triggers have significantly improved poisoning efficiency, but there is still room for improvement. Recently, selecting efficient samples has shown promise, but it requires a proxy backdoor injection task to find an efficient poisoned sample set, which can lead to performance degradation if the proxy attack settings are different from the actual settings used by the victims. In this paper, we propose a novel Proxy-Free Strategy (PFS) that selects efficient poisoned samples based on individual similarity and set diversity, effectively addressing this issue. We evaluate the proposed strategy on several datasets, triggers, poisoning ratios, architectures, and training hyperparameters. Our experimental results demonstrate that PFS achieves higher backdoor attack strength while x500 faster than previous proxy-based selection approaches.


page 3

page 5

page 12


Data-Efficient Backdoor Attacks

Recent studies have proven that deep neural networks are vulnerable to b...

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

Recent deep neural networks (DNNs) have come to rely on vast amounts of ...

Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy

Data-poisoning based backdoor attacks aim to insert backdoor into models...

Simple and Efficient Partial Graph Adversarial Attack: A New Perspective

As the study of graph neural networks becomes more intensive and compreh...

Enemy At the Gateways: A Game Theoretic Approach to Proxy Distribution

A core technique used by popular proxy-based circumvention systems like ...

Informative Sample-Aware Proxy for Deep Metric Learning

Among various supervised deep metric learning methods proxy-based approa...

Balanced Filtering via Non-Disclosive Proxies

We study the problem of non-disclosively collecting a sample of data tha...

Please sign up or login with your details

Forgot password? Click here to reset