paper-with-me

Papers

Injecting Bias into Text Classification Models using Backdoor Attacks

2024-12-25 · A. Dilara Yavuz, M. Emre Gursoy

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an attacker embeds a trigger into the victim model to make the model predict attacker-desired labels in targeted scenarios. In this paper, we propose to utilize backdoor attacks for a new purpose: bias injection. We develop a backdoor attack in which a subset of the training dataset is poisoned to associate strong male actors with negative sentiment. We execute our attack on two popular text classification datasets (IMDb and SST) and seven different models ranging from traditional Doc2Vec-based models to LSTM networks and modern transformer-based BERT and RoBERTa models. Our results show that the reduction in backdoored models' benign classification accuracy is limited, implying that our attacks remain stealthy, whereas the models successfully learn to associate strong male actors with negative sentiment (100% attack success rate with >= 3% poison rate). Attacks on BERT and RoBERTa are particularly more stealthy and effective, demonstrating an increased risk of using modern and larger models. We also measure the generalizability of our bias injection by proposing two metrics: (i) U-BBSR which uses previously unseen words when measuring attack success, and (ii) P-BBSR which measures attack success using paraphrased test samples. U-BBSR and P-BBSR results show that the bias injected by our attack can go beyond memorizing a trigger phrase.

📄 PDF Abstract BibTeX arXiv:2412.18975

Code (0)

등록된 구현이 없습니다.

Tasks

Backdoor Attacktext-classificationText Classification

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Tanh Activation 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Explainability-based Backdoor Attacks Against Graph Neural Networks

2021-04-08 · Jing Xu, Minhui, Xue, Stjepan Picek

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs.…

Backdoor AttackNode ClassificationPosition

Rethinking the Trigger-injecting Position in Graph Backdoor Attack

2023-04-05 · Jing Xu, Gorka Abad, Stjepan Picek

Backdoor attacks have been demonstrated as a security threat for machine learning models. Traditional backdoor attacks intend to inject backdoor functionality into the model such that the backdoored model will perform ab…

Backdoor AttackPosition

Label-Consistent Backdoor Attacks

2019-12-05 · Alexander Turner, Dimitris Tsipras, Aleksander Madry

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoo…

Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection

2025-08-04 · Wenjie Li, Siying Gu, Yiming Li, Shuxin Li 외 arxiv

Backdoor detection is currently the mainstream defense against backdoor attacks in federated learning (FL), where a small number of malicious clients can upload poisoned updates to compromise the federated global model. …

Federated Learning

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models

2025-10-11 · Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou 외 arxiv

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, w…