A Grey-box Text Attack Framework using Explainable AI
Explainable AI is a strong strategy implemented to understand complex black-box model predictions in a human interpretable language. It provides the evidence required to execute the use of trustworthy and reliable AI systems. On the other hand, however, it also opens the door to locating possible vulnerabilities in an AI model. Traditional adversarial text attack uses word substitution, data augmentation techniques and gradient-based attacks on powerful pre-trained Bidirectional Encoder Representations from Transformers (BERT) variants to generate adversarial sentences. These attacks are generally whitebox in nature and not practical as they can be easily detected by humans E.g. Changing the word from "Poor" to "Rich". We proposed a simple yet effective Grey-box cum Black-box approach that does not require the knowledge of the model while using a set of surrogate Transformer/BERT models to perform the attack using Explainable AI techniques. As Transformers are the current state-of-the-art models for almost all Natural Language Processing (NLP) tasks, an attack generated from BERT1 is transferable to BERT2. This transferability is made possible due to the attention mechanism in the transformer that allows the model to capture long-range dependencies in a sequence. Using the power of BERT generalisation via attention, we attempt to exploit how transformers learn by attacking a few surrogate transformer variants which are all based on a different architecture. We demonstrate that this approach is highly effective to generate semantically good sentences by changing as little as one word that is not detectable by humans while still fooling other BERT models.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial TextData AugmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Grey-box Adversarial Attack And Defence For Sentiment Classification
We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in…
Adversarial AttackClassificationGeneral ClassificationSentiment Analysis+1Malware Evasion Attack and Defense
Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate…
BIG-bench Machine LearningMalware DetectionDefending Grey Attacks by Exploiting Wavelet Analysis in Collaborative Filtering Recommender Systems
"Shilling" attacks or "profile injection" attacks have always major challenges in collaborative filtering recommender systems (CFRSs). Many efforts have been devoted to improve collaborative filtering techniques which ca…
Collaborative FilteringRecommendation SystemsMembership Inference Attacks on Discrete Diffusion Language Models
Masked Diffusion Language Models MDLMs replace autoregressive generation with iterative demasking and their privacy properties are largely unstudied. We study membership inference attacks MIA on fine tuned MDLMs and show…
Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification
Although Deep Neural Networks (DNNs) have great generalization and prediction capabilities, their functioning does not allow a detailed explanation of their behavior. Opaque deep learning models are increasingly used to …
Explainable artificial intelligenceExplainable Artificial Intelligence (XAI)image-classificationImage Classification