paper-with-me

홈 › Papers

Fast Adversarial Training against Textual Adversarial Attacks

2024-01-23 · Yichen Yang, Xin Liu, Kun He

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates used by attackers are accessible, which is an ideal assumption. We delve into adversarial training in the embedding space and propose a Fast Adversarial Training (FAT) method to improve the model robustness in the synonym-unaware scenario from the perspective of single-step perturbation generation and perturbation initialization. Based on the observation that the adversarial perturbations crafted by single-step and multi-step gradient ascent are similar, FAT uses single-step gradient ascent to craft adversarial examples in the embedding space to expedite the training process. Based on the observation that the perturbations generated on the identical training sample in successive epochs are similar, FAT fully utilizes historical information when initializing the perturbation. Extensive experiments demonstrate that FAT significantly boosts the robustness of BERT models in the synonym-unaware scenario, and outperforms the defense baselines under various attacks with character-level and word-level modifications.

📄 PDF Abstract BibTeX arXiv:2401.12461

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial DefenseAdversarial Robustness

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
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…
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.
Multi-Head Attention 설명 없음
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…

Similar Papers 제목 키워드 기반

Robust Textual Embedding against Word-level Adversarial Attacks

2022-02-28 · Yichen Yang, Xiaosen Wang, Kun He

We attribute the vulnerability of natural language processing models to the fact that similar inputs are converted to dissimilar representations in the embedding space, leading to inconsistent outputs, and we propose a n…

AttributeMetric LearningTriplet

Text Adversarial Purification as Defense against Adversarial Attacks

2022-03-27 · Linyang Li, Demin Song, Xipeng Qiu

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial pe…

Adversarial AttackAdversarial DefenseAdversarial Purification

AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning

2024-07-30 · Maisha Binte Rashid, Pablo Rivas

Multimodal machine learning models that combine visual and textual data are increasingly being deployed in critical applications, raising significant safety and security concerns due to their vulnerability to adversarial…

Adversarial RobustnessComputational EfficiencyDecoderImage Captioning

Role of Spatial Context in Adversarial Robustness for Object Detection

2019-09-30 · Aniruddha Saha, Akshayvarun Subramanya, Koninika Patil, Hamed Pirsiavash

The benefits of utilizing spatial context in fast object detection algorithms have been studied extensively. Detectors increase inference speed by doing a single forward pass per image which means they implicitly use con…

Adversarial AttackAdversarial RobustnessObjectobject-detection+2

MPAT: Building Robust Deep Neural Networks against Textual Adversarial Attacks

2024-02-29 · Fangyuan Zhang, Huichi Zhou, Shuangjiao Li, Hongtao Wang

Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks. However, previous defense…