相关论文: Towards Building a Robust Toxicity Predictor

Machine learning based solutions have been very helpful in solving problems that deal with immense amounts of data, such as malware detection and classification. However, deep neural networks have been found to be vulnerable to adversarial…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…

Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception,…

Insensitivity to semantically-preserving variations of prompts (paraphrases) is crucial for reliable behavior and real-world deployment of large language models. However, language models exhibit significant performance degradation when…

With the development of large language models (LLMs), detecting whether text is generated by a machine becomes increasingly challenging in the face of malicious use cases like the spread of false information, protection of intellectual…

Deep neural networks have been proven to be vulnerable to adversarial examples and various methods have been proposed to defend against adversarial attacks for natural language processing tasks. However, previous defense methods have…

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, making the detection of…

Text classification systems have continuously improved in performance over the years. However, nearly all current SOTA classifiers have a similar shortcoming, they process text in a horizontal manner. Vertically written words will not be…

We extend BeamAttack, an adversarial attack algorithm designed to evaluate the robustness of text classification systems through word-level modifications guided by beam search. Our extensions include support for word deletions and the…

Neural Machine Translation (NMT) models have been shown to be vulnerable to adversarial attacks, wherein carefully crafted perturbations of the input can mislead the target model. In this paper, we introduce ACT, a novel adversarial attack…

Large language models (LLMs) have exhibited remarkable fluency across various tasks. However, their unethical applications, such as disseminating disinformation, have become a growing concern. Although recent works have proposed a number of…

With the rapid development of Deep Neural Networks (DNNs), they have been applied in numerous fields. However, research indicates that DNNs are susceptible to adversarial examples, and this is equally true in the multi-label domain. To…

We introduce a simple yet efficient sentence-level attack on black-box toxicity detector models. By adding several positive words or sentences to the end of a hateful message, we are able to change the prediction of a neural network and…

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become the primary defense strategy, most studies focus on…

Recent efforts within the AI community have yielded impressive results towards "soft theorem proving" over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving…

Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and…

A growing line of work has investigated the development of neural NLP models that can produce rationales--subsets of input that can explain their model predictions. In this paper, we ask whether such rationale models can also provide…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…