Related papers: Rethinking the Intermediate Features in Adversaria…

Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced…

Language models (LMs) are indispensable tools for natural language processing tasks, but their vulnerability to adversarial attacks remains a concern. While current research has explored adversarial training techniques, their improvements…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

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…

Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…

Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of…

Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not…

Adversarial training is an approach of increasing the robustness of models to adversarial attacks by including adversarial examples in the training set. One major challenge of producing adversarial examples is to contain sufficient…

The emergence of vision-language-action models (VLAs) for end-to-end control is reshaping the field of robotics by enabling the fusion of multimodal sensory inputs at the billion-parameter scale. The capabilities of VLAs stem primarily from…

Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent…

We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Transfer learning across domains with distribution shift remains a fundamental challenge in building robust and adaptable machine learning systems. While adversarial perturbations are traditionally viewed as threats that expose model…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…