相关论文: Reliable Disentanglement Multi-view Learning Again…

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply when sensors fail or are noisy. We present Robust…

In the past decades, intensive efforts have been put to design various loss functions and metric forms for metric learning problem. These improvements have shown promising results when the test data is similar to the training data. However,…

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Multi-view learning is a learning problem that utilizes the various representations of an object to mine valuable knowledge and improve the performance of learning algorithm, and one of the significant directions of multi-view learning is…

Penetration Testing plays a critical role in evaluating the security of a target network by emulating real active adversaries. Deep Reinforcement Learning (RL) is seen as a promising solution to automating the process of penetration tests…

Autonomous driving systems (ADS) increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign…

We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcement learning (DRL) and is also important for rolling out…

In recent years, Deep Neural Network models have been developed in different fields, where they have brought many advances. However, they have also started to be used in tasks where risk is critical. A misdiagnosis of these models can lead…

Recently, robust reinforcement learning (RL) methods against input observation have garnered significant attention and undergone rapid evolution due to RL's potential vulnerability. Although these advanced methods have achieved reasonable…

Top-$k$ multi-label learning, which returns the top-$k$ predicted labels from an input, has many practical applications such as image annotation, document analysis, and web search engine. However, the vulnerabilities of such algorithms with…

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the…

The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…

Unlearning in Large Language Models (LLMs) aims to enhance safety, mitigate biases, and comply with legal mandates, such as the right to be forgotten. However, existing unlearning methods are brittle: minor query modifications, such as…

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that…

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…

Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition. While traditional multi-modal learning offers excellent recognition results, its computational…

Adversarial perturbations are critical for certifying the robustness of deep learning models. A universal adversarial perturbation (UAP) can simultaneously attack multiple images, and thus offers a more unified threat model, obviating an…

Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely…