CheckHARD: Checking Hard Labels for Adversarial Text Detection, Prediction Correction, and Perturbed Word Suggestion (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work detects adversarial text and corrects the prediction by identifying perturbed words and changing them into their synonyms, but many benign words are also changed. |
| Approach: | They propose to detect adversarial text, correct the prediction, and suggest perturbed words by checking the change in the hard labels from the target’s predictions. |
| Outcome: | The proposed model outperforms existing work on various attacks, models, and datasets. |
Similar Papers
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting adversarial attacks need original/adversarial data. |
| Approach: | They propose to detect adversarial text by voting on hard labels from predictions of transformations using a model that uses original/adversarial data. |
| Outcome: | The proposed method detects adversarial text across various state-of-the-art attacks, models, and datasets without training. |
Combating Adversarial Misspellings with Robust Word Recognition (P19-1)
Copied to clipboard
| Challenge: | a sub-field of word recognition models is emerging to combat adversarial spelling mistakes . imperceptible attacks can cause models to misclassify examples, but training robust models remains a challenge . |
| Approach: | They propose to place a word recognition model in front of a downstream classifier to combat adversarial spelling mistakes. |
| Outcome: | The proposed model outperforms adversarial training and off-the-shelf spell checkers in a word recognition task. |
In and Out-of-Domain Text Adversarial Robustness via Label Smoothing (2023.acl-short)
Copied to clipboard
| Challenge: | Existing studies show that state-of-the-art NLP models are vulnerable to adversarial attacks . label smoothing has been proven effective in a variety of applications and modalities . |
| Approach: | They propose to use label smoothing to improve adversarial robustness in pre-trained models against various popular attacks. |
| Outcome: | The proposed method significantly improves adversarial robustness in pre-trained models against various popular attacks. |
TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing textual adversarial attacks use gradient or prediction confidence to generate adversarials, making it hard to be deployed in real-world applications. |
| Approach: | They propose a textual adversarial attack that randomly perturbs lots of words to craft an adversarial example. |
| Outcome: | The proposed attack outperforms existing hard-label attacks in terms of attack performance and adversary quality. |
Towards Building a Robust Toxicity Predictor (2023.acl-industry)
Copied to clipboard
| Challenge: | Recent studies have focused on robustness of toxicity language predictors, but this is problematic for real-world toxicity detection. |
| Approach: | They propose a novel adversarial attack that exploits greedy search strategies to fool toxic text classifiers. |
| Outcome: | The proposed attack can detect weaker toxicity language detectors even against unseen attacks. |
Random Smooth-based Certified Defense against Text Adversarial Attack (2024.findings-eacl)
Copied to clipboard
| Challenge: | Textual adversarial examples train models on the worst-case text generated by substituting words in original texts with synonyms, but due to the discrete word embedding representations, the large search space hinders the robust training efficiency. |
| Approach: | They propose to treat the word substitution as a continuous perturbation on the word embedding representation and apply random smooth techniques to approximate the word replacement operation. |
| Outcome: | The proposed method outperforms conventional methods and improves the robustness in training. |
The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. |
| Approach: | They propose a novel approach to repair adversarial examples using an adversarial detector. |
| Outcome: | The proposed approach is effective in various adversarial attack scenarios. |
Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification (D19-1)
Copied to clipboard
| Challenge: | Existing studies on adversarial attacks on deep learning models focus on generation of adversarials and defense against adversarial attacks. |
| Approach: | They propose a framework to identify and adjust malicious perturbations and block adversarial attacks for machine learning models. |
| Outcome: | The proposed framework outperforms baseline methods in blocking adversarial attacks for text classification models. |
Are AI-Generated Text Detectors Robust to Adversarial Perturbations? (2024.acl-long)
Copied to clipboard
| Challenge: | Existing detectors for AI-generated text lack robustness against adversarial perturbations, with even minor changes in characters or words causing a reversal in distinguishing between human-created and AI-generated text. |
| Approach: | They propose a siamese calibration technique to train the model to make equally confident predictions under different noise, which improves the model’s robustness against adversarial perturbations. |
| Outcome: | The proposed detector outperforms baseline methods on four datasets and is more generalizable in cross-domain, cross-genre, and mixed-source scenarios. |
BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks (2025.findings-naacl)
Copied to clipboard
| Challenge: | Phishing often targets victims through visually perturbed texts to bypass security systems . previous studies have used synthetic datasets that do not contain real-world phishing cases . |
| Approach: | They propose a visual perturbation dataset to target phishing attacks using visual perturbations. |
| Outcome: | The proposed dataset includes real-world phishing cases annotated with visual perturbations . language models trained on the proposed dataset achieved an accuracy of approximately 96% . |