paper-with-me

홈 › Papers

SemAttack: Natural Textual Attacks via Different Semantic Spaces

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rates or fail to search efficiently in the exponentially large perturbation space. We propose an efficient and effective framework SemAttack to generate natural adversarial text by constructing different semantic perturbation functions. In particular, SemAttack optimizes the generated perturbations constrained on generic semantic spaces, including typo space, knowledge space (e.g., WordNet), contextualized semantic space (e.g., the embedding space of BERT clusterings), or the combination of these spaces. Thus, the generated adversarial texts are more semantically close to the original inputs. Extensive experiments reveal that state-of-the-art (SOTA) large-scale LMs (e.g., DeBERTa-v2) and defense strategies (e.g., FreeLB) are still vulnerable to SemAttack. We further demonstrate that SemAttack is general and able to generate natural adversarial texts for different languages (e.g., English and Chinese) with high attack success rates. Human evaluations also confirm that our generated adversarial texts are natural and barely affect human performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Text

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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
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.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

SemAttack: Natural Textual Attacks via Different Semantic Spaces

2022-05-03 · Findings (NAACL) 2022 7 · Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng 외

Recent studies show that pre-trained language models (LMs) are vulnerable to textual adversarial attacks. However, existing attack methods either suffer from low attack success rates or fail to search efficiently in the …

Adversarial Text

Adversarial Text Generation with Dynamic Contextual Perturbation

2025-06-10 · Hetvi Waghela, Jaydip Sen, Sneha Rakshit, Subhasis Dasgupta

Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing m…

Adversarial TextText Generation

A Simple General Method for Detecting Textual Adversarial Examples

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

Although deep neural networks have achieved state-of-the-art performance in various machine learning and artificial intelligence tasks, adversarial examples, constructed by adding small non-random perturbations to correc…

Ensemble LearningRepresentation LearningSentence

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 Attackbackdoor defense

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

2023-05-22 · CVPR 2023 1 · Simin Li, Shuing Zhang, Gujun Chen, Dong Wang 외

Physical world adversarial attack is a highly practical and threatening attack, which fools real world deep learning systems by generating conspicuous and maliciously crafted real world artifacts. In physical world attac…

Adversarial AttackAutonomous DrivingBenchmarking