paper-with-me

홈 › Papers

BERT-ATTACK: Adversarial Attack Against BERT Using BERT

2020-04-21 · EMNLP 2020 11 · Linyang Li, Ruotian Ma, Qipeng Guo, xiangyang xue, Xipeng Qiu

Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current successful attack methods for texts usually adopt heuristic replacement strategies on the character or word level, which remains challenging to find the optimal solution in the massive space of possible combinations of replacements while preserving semantic consistency and language fluency. In this paper, we propose \textbf{BERT-Attack}, a high-quality and effective method to generate adversarial samples using pre-trained masked language models exemplified by BERT. We turn BERT against its fine-tuned models and other deep neural models in downstream tasks so that we can successfully mislead the target models to predict incorrectly. Our method outperforms state-of-the-art attack strategies in both success rate and perturb percentage, while the generated adversarial samples are fluent and semantically preserved. Also, the cost of calculation is low, thus possible for large-scale generations. The code is available at https://github.com/LinyangLee/BERT-Attack.

📄 PDF Abstract BibTeX arXiv:2004.09984

Code (4)

LinyangLee/BERT-Attack 공식 구현 pytorch
QData/TextAttack 공식 구현 tf
Zoky-2020/Set-level_Guidance_Attack pytorch
xmc-aalto/adv-xmtc pytorch

Tasks

Adversarial Attack

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 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 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.
Weight Decay 설명 없음
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 &…
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

Similar Papers 제목 키워드 기반

Enhancing Adversarial Text Attacks on BERT Models with Projected Gradient Descent

2024-07-29 · Hetvi Waghela, Jaydip Sen, Sneha Rakshit

Adversarial attacks against deep learning models represent a major threat to the security and reliability of natural language processing (NLP) systems. In this paper, we propose a modification to the BERT-Attack framewor…

Adversarial TextSemantic SimilaritySemantic Textual Similarity

Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks

2021-07-15 · Findings (NAACL) 2022 7 · Zhao Meng, Yihan Dong, Mrinmaya Sachan, Roger Wattenhofer

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning…

Adversarial AttackContrastive LearningLanguage Modelling

FireBERT: Hardening BERT-based classifiers against adversarial attack

2020-08-10 · Gunnar Mein, Kevin Hartman, Andrew Morris

We present FireBERT, a set of three proof-of-concept NLP classifiers hardened against TextFooler-style word-perturbation by producing diverse alternatives to original samples. In one approach, we co-tune BERT against the…

Adversarial Attack

Learning to Ignore Adversarial Attacks

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that can explicitly…

Data Augmentation

Learning to Ignore Adversarial Attacks

2022-05-23 · Yiming Zhang, Yangqiaoyu Zhou, Samuel Carton, Chenhao Tan

Despite the strong performance of current NLP models, they can be brittle against adversarial attacks. To enable effective learning against adversarial inputs, we introduce the use of rationale models that can explicitly…

Data Augmentation