Challenge: Existing sentences use either no feedback or only the class labels for sentence-level attacks.
Approach: They propose an algorithm that uses class probabilities for black-box sentence-level attacks and investigate the effectiveness of using class probabilties on the attack’s success.
Outcome: The proposed algorithm is evaluated against baselines and classifiers and compares with the existing models to determine whether it is worthy or practical to use class probabilities for black-box sentence-level attacks.

Similar Papers

No offence, Bert - I insult only humans! Multilingual sentence-level attack on toxicity detection networks (2023.findings-emnlp)

Copied to clipboard

Challenge: a new sentence-level attack on toxic detection models is shown to work on seven languages . toxicity detection systems are used to silence the voices of criticism, causing echo chambers .
Approach: They propose a sentence-level attack that adds positive words to a hateful message . they show the attack works on seven languages from three different language families .
Outcome: The proposed attack is shown to work on seven languages from three different language families.
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.
Adversarial Attack and Defense of Structured Prediction Models (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to building effective adversarial attackers focus on classification problems.
Approach: They propose a framework that learns to attack a structured prediction model with feedbacks from multiple reference models.
Outcome: The proposed framework is able to attack state-of-the-art models and boost them with training . it is based on a sequence-to-sequence model with feedbacks from multiple reference models .
Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in natural language processing have highlighted the vulnerability of deep learning models to adversarial attacks.
Approach: They propose a benchmark for textual adversarial defence that evaluates state-of-the-art defence mechanisms across diverse datasets, models, and tasks.
Outcome: The proposed benchmark incorporates a wide range of datasets and evaluates state-of-the-art defence mechanisms.
RobustSentEmbed: Robust Sentence Embeddings Using Adversarial Self-Supervised Contrastive Learning (2024.findings-naacl)

Copied to clipboard

Challenge: Existing pre-trained language models exhibit poor generalization and robustness in adversarial settings.
Approach: They propose a self-supervised sentence embedding framework that improves generalization and robustness against adversarial attacks.
Outcome: The proposed framework reduces the success rate of adversarial attacks by almost half . it also improves semantic text similarity tasks and various transfer tasks .
SHARP: Search-Based Adversarial Attack for Structured Prediction (2022.findings-naacl)

Copied to clipboard

Challenge: SHARP is a new attack method for structured prediction models that solves several challenges.
Approach: They propose a black-box adversarial attack method that uses a search-based optimization problem to attack adversarials.
Outcome: The proposed method performs more potent attack than pioneer arts on two structured prediction tasks.
Phrase-level Textual Adversarial Attack with Label Preservation (2022.findings-naacl)

Copied to clipboard

Challenge: Existing adversarial attacks are usually realized through word-level or sentence-level perturbations, which either limit the perturbation space or sacrifice fluency and textual quality.
Approach: They propose a phrase-level perturbation-based adversarial ATtack that generates adversarials through phrase- level perturbations.
Outcome: The proposed approach improves the performance of natural language processing models by reducing the need for word-level perturbations and preserving the fluency and grammaticality of the samples.
Evaluating Neural Model Robustness for Machine Comprehension (2021.eacl-main)

Copied to clipboard

Challenge: evaluating model robustness to adversarial attacks can provide deeper understanding of how deep neural networks work and what kind of linguistic information is actually captured by neural networks.
Approach: They propose a method for strategic sentence-level perturbations to evaluate model robustness to adversarial attacks using character and word perturbations.
Outcome: The proposed model improves model performance during adversarial attacks by using ensembles and predicts errors in adversarials.
HotFlip: White-Box Adversarial Examples for Text Classification (P18-2)

Copied to clipboard

Challenge: Existing methods to create adversarial examples without explicit knowledge of model parameters are not effective.
Approach: They propose an efficient method to generate white-box adversarial examples to trick a character-level neural classifier by an atomic flip operation.
Outcome: The proposed method can be adapted to attack a word-level classifier with a few constraints.
From Hero to Zéroe: A Benchmark of Low-Level Adversarial Attacks (2020.aacl-main)

Copied to clipboard

Challenge: Adversarial attacks are label-preserving modifications to inputs of machine learning classifiers designed to fool machines but not humans.
Approach: They propose to use a dataset to test the robustness of future NLP models to identify low-level adversarial attacks that are less realistic in typical applications such as social media.
Outcome: The proposed dataset provides a benchmark for testing robustness of future more human-like NLP models.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations