Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
Backdoor attacks pose a significant threat to the integrity of text classification models used in natural language processing. While several dirty-label attacks that achieve high attack success rates (ASR) have been proposed, clean-label attacks are inherently more difficult. In this paper, we propose three sample selection strategies to improve attack effectiveness in clean-label scenarios: Minimum, Above50, and Below50. Our strategies identify those samples which the model predicts incorrectly or with low confidence, and by injecting backdoor triggers into such samples, we aim to induce a stronger association between the trigger patterns and the attacker-desired target label. We apply our methods to clean-label variants of four canonical backdoor attacks (InsertSent, WordInj, StyleBkd, SynBkd) and evaluate them on three datasets (IMDB, SST2, HateSpeech) and four model types (LSTM, BERT, DistilBERT, RoBERTa). Results show that the proposed strategies, particularly the Minimum strategy, significantly improve the ASR over random sample selection with little or no degradation in the model's clean accuracy. Furthermore, clean-label attacks enhanced by our strategies outperform BITE, a state of the art clean-label attack method, in many configurations.
Code (0)
등록된 구현이 없습니다.
Tasks
Text ClassificationSimilar Papers 제목 키워드 기반
ProMix: Combating Label Noise via Maximizing Clean Sample Utility
Learning with Noisy Labels (LNL) has become an appealing topic, as imperfectly annotated data are relatively cheaper to obtain. Recent state-of-the-art approaches employ specific selection mechanisms to separate clean an…
Learning with noisy labelsA Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{trigger…
Active label cleaning for improved dataset quality under resource constraints
Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, emp…
Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning
Learning with noisy labels (LNL) has been extensively studied, with existing approaches typically following a framework that alternates between clean sample selection and semi-supervised learning (SSL). However, this app…
Learning with noisy labelsPASS: Peer-Agreement based Sample Selection for training with Noisy Labels
The prevalence of noisy-label samples poses a significant challenge in deep learning, inducing overfitting effects. This has, therefore, motivated the emergence of learning with noisy-label (LNL) techniques that focus on…