相关论文: Cyberbullying Classifiers are Sensitive to Model-A…

Cyberbullying is a disturbing online misbehaviour with troubling consequences. It appears in different forms, and in most of the social networks, it is in textual format. Automatic detection of such incidents requires intelligent systems.…

Adversarial examples are malicious inputs crafted to cause a model to misclassify them. Their most common instantiation, "perturbation-based" adversarial examples introduce changes to the input that leave its true label unchanged, yet…

"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning community. To explain this surprising phenomenon, a series of works…

An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their power to discriminate toxic sentences,…

Due to language models' propensity to generate toxic or hateful responses, several techniques were developed to align model generations with users' preferences. Despite the effectiveness of such methods in improving the safety of model…

Given the great success of Deep Neural Networks(DNNs) and the black-box nature of it,the interpretability of these models becomes an important issue.The majority of previous research works on the post-hoc interpretation of a trained…

Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

Detecting ambiguity is important for language understanding, including uncertainty estimation, humour detection, and processing garden path sentences. We assess language models' sensitivity to ambiguity by introducing an adversarial…

Despite significant ongoing efforts in safety alignment, large language models (LLMs) such as GPT-4 and LLaMA 3 remain vulnerable to jailbreak attacks that can induce harmful behaviors, including through the use of adversarial suffixes.…

Large language models (LLMs) are known to exhibit brittle behavior under adversarial prompts and jailbreak attacks, even after extensive alignment and fine-tuning. This fragility reflects a broader challenge of modern neural language…

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

It is well known that the usefulness of a machine learning model is due to its ability to generalize to unseen data. This study uses three popular cyberbullying datasets to explore the effects of data, how it's collected, and how it's…

As large language models (LLMs) have been deployed in various real-world settings, concerns about the harm they may propagate have grown. Various jailbreaking techniques have been developed to expose the vulnerabilities of these models and…

Real-world natural language processing systems need to be robust to human adversaries. Collecting examples of human adversaries for training is an effective but expensive solution. On the other hand, training on synthetic attacks with small…

The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language…

Recently, generating adversarial examples has become an important means of measuring robustness of a deep learning model. Adversarial examples help us identify the susceptibilities of the model and further counter those vulnerabilities by…

Detecting harmful and non-inclusive terminology in technical contexts is critical for fostering inclusive environments in computing. This study explores the impact of model architecture on harmful language detection by evaluating a curated…

Large Language Model (LLM) based judges form the underpinnings of key safety evaluation processes such as offline benchmarking, automated red-teaming, and online guardrailing. This widespread requirement raises the crucial question: can we…