Related papers: Forging the Forger: An Attempt to Improve Authorsh…

Some of the most popular methods for improving the stability and performance of GANs involve constraining or regularizing the discriminator. In this paper we consider a largely overlooked regularization technique which we refer to as the…

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Attackers can deliberately perturb classifiers' input with subtle noise, altering final predictions. Among proposed countermeasures, adversarial purification employs generative networks to preprocess input images, filtering out adversarial…

Adversarial examples cause neural networks to produce incorrect outputs with high confidence. Although adversarial training is one of the most effective forms of defense against adversarial examples, unfortunately, a large gap exists…

Text-aware recommender systems incorporate rich textual features, such as titles and descriptions, to generate item recommendations for users. The use of textual features helps mitigate cold-start problems, and thus, such recommender…

The PAN 2020 authorship verification (AV) challenge focuses on a cross-topic/closed-set AV task over a collection of fanfiction texts. Fanfiction is a fan-written extension of a storyline in which a so-called fandom topic describes the…

In this work, we consider one challenging training time attack by modifying training data with bounded perturbation, hoping to manipulate the behavior (both targeted or non-targeted) of any corresponding trained classifier during test time…

The recent success of large language models for text generation poses a severe threat to academic integrity, as plagiarists can generate realistic paraphrases indistinguishable from original work. However, the role of large autoregressive…

Randomized smoothing has become a leading method for achieving certified robustness in deep classifiers against l_{p}-norm adversarial perturbations. Current approaches for achieving certified robustness, such as data augmentation with…

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as…

High-quality text generation capability of recent Large Language Models (LLMs) causes concerns about their misuse (e.g., in massive generation/spread of disinformation). Machine-generated text (MGT) detection is important to cope with such…

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial perturbations…

Authorship representation (AR) learning, which models an author's unique writing style, has demonstrated strong performance in authorship attribution tasks. However, prior research has primarily focused on monolingual settings-mostly in…

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs.…

Pre-trained transformer models such as BERT have shown massive gains across many text classification tasks. However, these models usually need enormous labeled data to achieve impressive performances. Obtaining labeled data is often…

We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based models. We evaluate our approach on three datasets, comparing…

Deep Imitation Learning requires a large number of expert demonstrations, which are not always easy to obtain, especially for complex tasks. A way to overcome this shortage of labels is through data augmentation. However, this cannot be…

Data augmentation, the artificial creation of training data for machine learning by transformations, is a widely studied research field across machine learning disciplines. While it is useful for increasing a model's generalization…

Authorship verification (AV) aims to identify whether a pair of texts has the same author. We address the challenge of evaluating AV models' robustness against topic shifts. The conventional evaluation assumes minimal topic overlap between…

We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for…