Related papers: Unifying Adversarial Robustness and Training Acros…
As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…
Large Language Models (LLMs) have demonstrated impressive capabilities in natural language tasks, but their safety and morality remain contentious due to their training on internet text corpora. To address these concerns, alignment…
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…
Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…
Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However,…
Deep Neural Networks are vulnerable to adversarial attacks. Among many defense strategies, adversarial training with untargeted attacks is one of the most effective methods. Theoretically, adversarial perturbation in untargeted attacks can…
As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI).…
Adversarial training provides a means of regularizing supervised learning algorithms while virtual adversarial training is able to extend supervised learning algorithms to the semi-supervised setting. However, both methods require making…
As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital.…
The vulnerability of deep neural networks to imperceptible adversarial perturbations has attracted widespread attention. Inspired by the success of vision-language foundation models, previous efforts achieved zero-shot adversarial…
The increasing reliance on large language models (LLMs) for diverse applications necessitates a thorough understanding of their robustness to adversarial perturbations and out-of-distribution (OOD) inputs. In this study, we investigate the…
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…
Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…
Recent work has explored integrating autoregressive language models with energy-based models (EBMs) to enhance text generation capabilities. However, learning effective EBMs for text is challenged by the discrete nature of language. This…
Machine learning and deep learning in particular has been recently used to successfully address many tasks in the domain of code such as finding and fixing bugs, code completion, decompilation, type inference and many others. However, the…
With the widespread use of machine learning, concerns over its security and reliability have become prevalent. As such, many have developed defenses to harden neural networks against adversarial examples, imperceptibly perturbed inputs that…
Adversarial training has been shown to be reliable in improving robustness against adversarial samples. However, the problem of adversarial training in terms of fairness has not yet been properly studied, and the relationship between…
Adversarial examples can cause catastrophic mistakes in Deep Neural Network (DNNs) based vision systems e.g., for classification, segmentation and object detection. The vulnerability of DNNs against such attacks can prove a major roadblock…
Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning models in terms of fairness, robustness, and generalization is…
Adversarial examples, generated by applying small perturbations to input features, are widely used to fool classifiers and measure their robustness to noisy inputs. However, little work has been done to evaluate the robustness of ranking…