Related papers: MockingBERT: A Method for Retroactively Adding Res…
It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…
In spite of great advancements of machine reading comprehension (RC), existing RC models are still vulnerable and not robust to different types of adversarial examples. Neural models over-confidently predict wrong answers to semantic…
Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically…
Large Language Models (LLMs) have emerged as powerful tools, but their inherent safety risks - ranging from harmful content generation to broader societal harms - pose significant challenges. These risks can be amplified by the recent…
Large-scale pre-trained language models such as BERT have contributed significantly to the development of NLP. However, those models require large computational resources, making it difficult to be applied to mobile devices where computing…
Adversarial learning has emerged as one of the successful techniques to circumvent the susceptibility of existing methods against adversarial perturbations. However, the majority of existing defense methods are tailored to defend against a…
We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT,…
Training large language models (LLMs) requires a substantial investment of time and money. To get a good return on investment, the developers spend considerable effort ensuring that the model never produces harmful and offensive outputs.…
Adversarial attacks for discrete data (such as texts) have been proved significantly more challenging than continuous data (such as images) since it is difficult to generate adversarial samples with gradient-based methods. Current…
Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating…
Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…
Large language models (LLMs) are pretrained on corpora containing trillions of tokens and, therefore, inevitably memorize sensitive information. Locate-then-edit methods, as a mainstream paradigm of model editing, offer a promising solution…
Pre-trained language models (PLMs) have consistently demonstrated outstanding performance across a diverse spectrum of natural language processing tasks. Nevertheless, despite their success with unseen data, current PLM-based…
Revealing the robustness issues of natural language processing models and improving their robustness is important to their performance under difficult situations. In this paper, we study the robustness of paraphrase identification models…
The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this…
Can language models transform inputs to protect text classifiers against adversarial attacks? In this work, we present ATINTER, a model that intercepts and learns to rewrite adversarial inputs to make them non-adversarial for a downstream…
Understanding covert narratives and implicit messaging is essential for analyzing bias and sentiment. Traditional NLP methods struggle with detecting subtle phrasing and hidden agendas. This study tackles two key challenges: (1) multi-label…
Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…
Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is imperative to gain a comprehensive understanding of the…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…