| Challenge: | Recent studies have exposed the vulnerability of text classification models to adversarial examples . perturbed versions of the original text are indiscernible by humans and misclassified by the model . |
| Approach: | They propose a black box attack for generating adversarial examples using contextual perturbations from a BERT-masked language model. |
| Outcome: | The proposed attack produces examples with improved grammaticality and semantic coherence compared to previous work. |
Similar Papers
BERT-ATTACK: Adversarial Attack Against BERT Using BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current approaches to generate adversarial samples for discrete data are heuristic replacement strategies that are difficult to implement in continuous data. |
| Approach: | They propose a method to generate adversarial samples using pre-trained masked language models using BERT. |
| Outcome: | The proposed method outperforms state-of-the-art methods in success rate and perturb percentage while remaining fluent and semantically preserved. |
Arabic Synonym BERT-based Adversarial Examples for Text Classification (2024.eacl-srw)
Copied to clipboard
| Challenge: | Often, research studies quantifying the impact of adversarial text attacks have been applied only to models trained in English. |
| Approach: | They propose a word-level study of adversarial text examples in Arabic . they use a synonym attack with a BERT model to assess their robustness . |
| Outcome: | The proposed attack compares Arabic adversarial examples with their original examples and regains 2% accuracy after training. |
Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to improve model robustness against word substitution-based adversarial attacks are too slow to generate adversarials on the fly. |
| Approach: | They propose an approach to improve the robustness of BERT models against word substitution-based adversarial attacks by leveraging adversarials for self-supervised contrastive learning. |
| Outcome: | The proposed method improves robustness of BERT models against word substitution-based adversarial attacks without using any labeled data. |
BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent efforts to generate adversaries using rule-based synonyms and BERT-MLMs have been witnessed in general domain, but the ever-increasing biomedical literature poses unique challenges. |
| Approach: | They propose a black-box attack algorithm for biomedical text classification that uses rule-based synonyms and BERT-MLMs to generate adversarial examples. |
| Outcome: | The proposed algorithm performs stronger with better language fluency and semantic coherence than previous work. |
GAN-BERT: Generative Adversarial Learning for Robust Text Classification with a Bunch of Labeled Examples (2020.acl-main)
Copied to clipboard
| Challenge: | Recent Transformer-based architectures provide impressive results in many NLP tasks, but obtaining high-quality annotated data is expensive and time consuming. |
| Approach: | They propose a semisupervised learning method that ex- tends the fine-tuning of BERT-like architectures with unlabeled data in a generative adversarial setting. |
| Outcome: | The proposed method reduces the requirement for annotated examples while achieving good performance in sentence classification tasks. |
Reevaluating Adversarial Examples in Natural Language (2020.findings-emnlp)
Copied to clipboard
| Challenge: | State-of-the-art adversarial examples lack a common definition of what constitutes success . human surveys show that to preserve semantics, we need to increase the minimum cosine similarities between the embeddings of swapped words and between the sentence encodings of original and perturbed sentences. |
| Approach: | They propose a unified definition of what constitutes a successful adversarial example . they propose four categories of constraints that are used to define adversarials . |
| Outcome: | The proposed framework is based on the outputs of two state-of-the-art synonym substitution attacks. |
On Adversarial Examples for Character-Level Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Using adversarial examples to measure robustness of deep learning models has become a standard procedure due to the difficulty of creating white-box adversarials for discrete text input. |
| Approach: | They propose two novel attacks which aim to remove or change a word in a translation, rather than simply break the NMT. |
| Outcome: | The proposed attacks are significantly stronger than their black-box counterparts in different attack scenarios, showing more serious vulnerabilities than previously known. |
BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks (2021.findings-acl)
Copied to clipboard
| Challenge: | adversarial attacks expose important blind spots of deep learning systems, authors show . word and sentence-level attacks tend to be more difficult to defend via spelling correction modules . character-level attack scenarios often involve finding semantic paraphrases of input . |
| Approach: | They propose a model that probabilistically combines context-independent word level information with context-dependent information from BERT's masked language modeling to combat low-level orthographic attacks. |
| Outcome: | The proposed model outperforms a spellchecker and Pruthi's model on a character-level benchmark. |
Contrasting Human- and Machine-Generated Word-Level Adversarial Examples for Text Classification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent work has raised the question of whether valid adversarial inputs are feasible. |
| Approach: | They analyze how human-generated adversarial examples compare to the best algorithms . they use crowdsourcing to modify words in an input text with immediate feedback . |
| Outcome: | The proposed algorithms are not more efficient than the best to generate natural-reading, sentiment-preserving examples. |
Generating Natural Language Adversarial Examples (D18-1)
Copied to clipboard
| Challenge: | Recent research has shown that deep neural networks are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. |
| Approach: | They propose to generate adversarial examples that fool well-trained sentiment analysis and textual entailment models by using a black-box population-based optimization algorithm. |
| Outcome: | The proposed model is able to fool well-trained sentiment analysis and textual entailment models with success rates of 97% and 70%, respectively. |