paper-with-me

홈 › Papers

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 learn to ignore attack tokens. We find that the rationale models can ignore over 90\% of attack tokens. This approach leads to consistent sizable improvements ($\sim$8\%) over baseline models in robustness, for both BERT and RoBERTa, on MultiRC and FEVER, and also reliably outperforms data augmentation with adversarial examples alone. In many cases, we find that our method is able to close the gap between model performance on a clean test set and an attacked test set, eliminating the effect of adversarial attacks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

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 &…
Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Weight Decay 설명 없음
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…
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

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

Attention for Adversarial Attacks: Learning from your Mistakes

2021-11-22 · AAAI Workshop AdvML 2022 2 · Florian Jaeckle, Aleksandr Agadzhanov, Jingyue Lu, M. Pawan Kumar

In order to apply Neural Networks in safety-critical settings, such as healthcare or autonomous driving, we need to be able to analyse their robustness against adversarial attacks. As complete verification is often compu…

Autonomous Driving

Smoothness Analysis of Adversarial Training

2021-03-02 · Sekitoshi Kanai, Masanori Yamada, Hiroshi Takahashi, Yuki Yamanaka 외

Deep neural networks are vulnerable to adversarial attacks. Recent studies about adversarial robustness focus on the loss landscape in the parameter space since it is related to optimization and generalization performanc…

Adversarial Robustness

Does Adversarial Robustness Really Imply Backdoor Vulnerability?

2021-09-29 · Yinghua Gao, Dongxian Wu, Jingfeng Zhang, Shu-Tao Xia 외

Recent research has revealed a trade-off between the robustness against adversarial attacks and backdoor attacks. Specifically, with the increasing adversarial robustness obtained through adversarial training, the model …

Adversarial Robustness

State-of-the-art optical-based physical adversarial attacks for deep learning computer vision systems

2023-03-22 · Junbin Fang, You Jiang, Canjian Jiang, Zoe L. Jiang 외

Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the co…

Adversarial Attack