Related papers: Nearest is Not Dearest: Towards Practical Defense …

With the increasing size of frontier LLMs, post-training quantization has become the standard for memory-efficient deployment. Recent work has shown that basic rounding-based quantization schemes pose security risks, as they can be…

ML is shifting from the cloud to the edge. Edge computing reduces the surface exposing private data and enables reliable throughput guarantees in real-time applications. Of the panoply of devices deployed at the edge, resource-constrained…

Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated to specific…

The advent of multimodal deep learning models, such as CLIP, has unlocked new frontiers in a wide range of applications, from image-text understanding to classification tasks. However, these models are not safe for adversarial attacks,…

Federated learning has seen increased adoption in recent years in response to the growing regulatory demand for data privacy. However, the opaque local training process of federated learning also sparks rising concerns about model…

Quantized neural networks (QNNs) are increasingly used for efficient deployment of deep learning models on resource-constrained platforms, such as mobile devices and edge computing systems. While quantization reduces model size and…

Federated learning (FL) enables multiple clients to collaboratively train deep learning models while considering sensitive local datasets' privacy. However, adversaries can manipulate datasets and upload models by injecting triggers for…

The introduction of robust optimisation has pushed the state-of-the-art in defending against adversarial attacks. Notably, the state-of-the-art projected gradient descent (PGD)-based training method has been shown to be universally and…

We present a new type of backdoor attack that exploits a vulnerability of convolutional neural networks (CNNs) that has been previously unstudied. In particular, we examine the application of facial recognition. Deep learning techniques are…

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectures. However, the backdoor attack on pre-trained models poses…

As machine learning techniques become increasingly prevalent in data analysis, the threat of adversarial attacks has surged, necessitating robust defense mechanisms. Among these defenses, methods exploiting low-rank approximations for input…

Variational quantum algorithms (VQAs) are a central paradigm for noisy intermediate-scale (NISQ) quantum computing, yet their reliance on predesigned and pretrained variational quantum circuits (VQCs) introduces critical security…

Hybrid Quantum Neural Networks (HQNNs) represent a promising advancement in Quantum Machine Learning (QML), yet their security has been rarely explored. In this paper, we present the first systematic study of backdoor attacks on HQNNs. We…

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

Recent studies have shown that deep neural networks (DNNs) are vulnerable to adversarial attacks. To this end, many defense approaches that attempt to improve the robustness of DNNs have been proposed. In a separate and yet related area,…

We propose a circuit-level backdoor attack, \textit{QTrojan}, against Quantum Neural Networks (QNNs) in this paper. QTrojan is implemented by few quantum gates inserted into the variational quantum circuit of the victim QNN. QTrojan is much…

Quantized Neural Networks (QNNs) have emerged as a promising solution for reducing model size and computational costs, making them well-suited for deployment in edge and resource-constrained environments. While quantization is known to…

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Post-training quantization attracts increasing attention due to its convenience in deploying quantized neural networks. Although rounding-to-nearest remains the prevailing method for DNN quantization, prior research has demonstrated its…

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These…