Related papers: CAT-Gen: Improving Robustness in NLP Models via Co…

Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machine learning through formal guarantees. However, recent breakthroughs in artificial…

Spurious correlations threaten the validity of statistical classifiers. While model accuracy may appear high when the test data is from the same distribution as the training data, it can quickly degrade when the test distribution changes.…

Adversarial attacks against deep learning models represent a major threat to the security and reliability of natural language processing (NLP) systems. In this paper, we propose a modification to the BERT-Attack framework, integrating…

Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode…

While recent works have been considerably improving the quality of the natural language explanations (NLEs) generated by a model to justify its predictions, there is very limited research in detecting and alleviating inconsistencies among…

Recently proposed BERT-based evaluation metrics for text generation perform well on standard benchmarks but are vulnerable to adversarial attacks, e.g., relating to information correctness. We argue that this stems (in part) from the fact…

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial examples. There is a need to build defenses that protect…

Despite the success of machine learning applications in science, industry, and society in general, many approaches are known to be non-robust, often relying on spurious correlations to make predictions. Spuriousness occurs when some…

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets (GAN) that…

Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controlling several stylistic aspects of the generated text, in addition to its content. The method is based…

Recent empirical studies show that adversarial topic models (ATM) can successfully capture semantic patterns of the document by differentiating a document with another dissimilar sample. However, utilizing that discriminative-generative…

In the era of widespread public use of AI systems across various domains, ensuring adversarial robustness has become increasingly vital to maintain safety and prevent undesirable errors. Researchers have curated various adversarial datasets…

In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services…

Generative adversarial networks (GANs) have proven effective in modeling distributions of high-dimensional data. However, their training instability is a well-known hindrance to convergence, which results in practical challenges in their…

Transformer-based language models excel in NLP tasks, but fine-grained control remains challenging. This paper explores methods for manipulating transformer models through principled interventions at three levels: prompts, activations, and…

We propose algorithms to create adversarial attacks to assess model robustness in text classification problems. They can be used to create white box attacks and black box attacks while at the same time preserving the semantics and syntax of…

Text classifiers are vulnerable to adversarial examples -- correctly-classified examples that are deliberately transformed to be misclassified while satisfying acceptability constraints. The conventional approach to finding adversarial…

Training adversarially robust discriminative (i.e., softmax) classifier has been the dominant approach to robust classification. Building on recent work on adversarial training (AT)-based generative models, we investigate using AT to learn…

Neural text detectors aim to decide the characteristics that distinguish neural (machine-generated) from human texts. To challenge such detectors, adversarial attacks can alter the statistical characteristics of the generated text, making…

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…