Attention-Enhancing Backdoor Attacks Against BERT-based Models

2023-10-23 · Weimin Lyu, Songzhu Zheng, Lu Pang, Haibin Ling, Chao Chen

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most existing textual backdoor attacks focus on generating stealthy triggers or modifying model weights. In this paper, we directly target the interior structure of neural networks and the backdoor mechanism. We propose a novel Trojan Attention Loss (TAL), which enhances the Trojan behavior by directly manipulating the attention patterns. Our loss can be applied to different attacking methods to boost their attack efficacy in terms of attack successful rates and poisoning rates. It applies to not only traditional dirty-label attacks, but also the more challenging clean-label attacks. We validate our method on different backbone models (BERT, RoBERTa, and DistilBERT) and various tasks (Sentiment Analysis, Toxic Detection, and Topic Classification).

📄 PDF Abstract BibTeX arXiv:2310.14480

Code (0)

등록된 구현이 없습니다.

Tasks

Sentiment AnalysisTopic Classification

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

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 $x$…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Adam 설명 없음

Residual Connection 설명 없음

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

2023-05-25 · Xuanli He, Jun Wang, Benjamin Rubinstein, Trevor Cohn

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks …

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models

2024-05-27 · Yuzhou. Nie, Yanting. Wang, Jinyuan. Jia, Michael J. De Lucia 외

One key challenge in backdoor attacks against large foundation models is the resource limits. Backdoor attacks usually require retraining the target model, which is impractical for very large foundation models. Existing …

Backdoor Attack GPU

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

2020-11-20 · EMNLP 2021 11 · Fanchao Qi, Yangyi Chen, Mukai Li, Yuan YAO 외

Backdoor attacks are a kind of emergent training-time threat to deep neural networks (DNNs). They can manipulate the output of DNNs and possess high insidiousness. In the field of natural language processing, some attack…

Backdoor Attack backdoor defense

Watch Out for the Lifespan: Evaluating Backdoor Attacks Against Federated Model Adaptation

2025-11-18 · Bastien Vuillod, Pierre-Alain Moellic, Jean-Max Dutertre arxiv

Large models adaptation through Federated Learning (FL) addresses a wide range of use cases and is enabled by Parameter-Efficient Fine-Tuning techniques such as Low-Rank Adaptation (LoRA). However, this distributed learn…

parameter-efficient fine-tuning Federated Learning

Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning

2025-01-22 · Mingyuan Fan, Zhanyi Hu, Fuyi Wang, Cen Chen

Data heterogeneity and backdoor attacks rank among the most significant challenges facing federated learning (FL). For data heterogeneity, personalized federated learning (PFL) enables each client to maintain a private p…

Federated Learning Personalized Federated Learning