Related papers: BadPatches: Routing-aware Backdoor Attacks on Visi…

Deep neural networks have been widely used in many critical applications, such as autonomous vehicles and medical diagnosis. However, their security is threatened by backdoor attacks, which are achieved by adding artificial patterns to…

Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the…

Recent deep-learning-based compression methods have achieved superior performance compared with traditional approaches. However, deep learning models have proven to be vulnerable to backdoor attacks, where some specific trigger patterns…

Sparsely-gated Mixture of Expert (MoE), an emerging deep model architecture, has demonstrated a great promise to enable high-accuracy and ultra-efficient model inference. Despite the growing popularity of MoE, little work investigated its…

Deepfakes have recently raised significant trust issues and security concerns among the public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the expressivity of transformers, achieving superior detection…

Recent studies have revealed the vulnerability of Deep Neural Networks (DNNs) to adversarial examples, which can easily fool DNNs into making incorrect predictions. To mitigate this deficiency, we propose a novel adversarial defense method…

Medical foundation models are gaining prominence in the medical community for their ability to derive general representations from extensive collections of medical image-text pairs. Recent research indicates that these models are…

Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing…

Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend on a superficial safety mechanism in which harmful inputs are routed safety-critical…

In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerability to backdoor attacks remains unexplored. To fill the gap in…

Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Adverse weather removal tasks like deraining, desnowing, and dehazing are usually treated as separate tasks. However, in practical autonomous driving scenarios, the type, intensity,and mixing degree of weather are unknown, so handling each…

The newly introduced Visual State Space Model (VMamba), which employs \textit{State Space Mechanisms} (SSM) to interpret images as sequences of patches, has shown exceptional performance compared to Vision Transformers (ViT) across various…

The Mixture-of-Experts (MoE) models have gained significant attention in deep learning due to their dynamic resource allocation and superior performance across diverse tasks. However, efficiently training these models remains challenging.…

Current federated backdoor attacks focus on collaboratively training backdoor triggers, where multiple compromised clients train their local trigger patches and then merge them into a global trigger during the inference phase. However,…

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of \emph{expert paths} -- the sequence of expert selections a token…

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Deep neural networks are vulnerable to backdoor attacks, where an adversary manipulates the model behavior through overlaying images with special triggers. Existing backdoor defense methods often require accessing a few validation data and…

Mixture-of-Experts (MoE) models provide a structured approach to combining specialized neural networks and offer greater interpretability than conventional ensembles. While MoEs have been successfully applied to image classification and…