相关论文: Nearest is Not Dearest: Towards Practical Defense …

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples,…

Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced…

Federated learning is a versatile framework for training models in decentralized environments. However, the trust placed in clients makes federated learning vulnerable to backdoor attacks launched by malicious participants. While many…

Neural code models have found widespread success in tasks pertaining to code intelligence, yet they are vulnerable to backdoor attacks, where an adversary can manipulate the victim model's behavior by inserting triggers into the source…

Federated Learning (FL) is a promising privacy-preserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the…

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain types of triggers or poisoning mechanisms. State-of-the-art (SOTA)…

The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption has fostered the…

Deep neural networks have played a crucial part in many critical domains, such as autonomous driving, face recognition, and medical diagnosis. However, deep neural networks are facing security threats from backdoor attacks and can be…

The success of a deep neural network (DNN) heavily relies on the details of the training scheme; e.g., training data, architectures, hyper-parameters, etc. Recent backdoor attacks suggest that an adversary can take advantage of such…

To explore the vulnerability of deep neural networks (DNNs), many attack paradigms have been well studied, such as the poisoning-based backdoor attack in the training stage and the adversarial attack in the inference stage. In this paper,…

Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their success in the…

Recent researches show that deep learning model is susceptible to backdoor attacks. Many defenses against backdoor attacks have been proposed. However, existing defense works require high computational overhead or backdoor attack…

Deep Neural Networks (DNNs) have been widely used in many areas such as autonomous driving and face recognition. However, DNN model is fragile to backdoor attack. A backdoor in the DNN model can be activated by a poisoned input with trigger…

Deep learning models are the most efficient models in many machine learning tasks. The main disadvantage when using them in IoT, mobile devices, independent autonomous or real-time systems is their complexity and memory size. Therefore,…

Neural backdoor attack is emerging as a severe security threat to deep learning, while the capability of existing defense methods is limited, especially for complex backdoor triggers. In the work, we explore the space formed by the pixel…

Quantum Machine Learning (QML) integrates quantum computational principles into learning algorithms, offering improved representational capacity and computational efficiency. However, the security and robustness of QML systems remain…

Recent successful adversarial attacks on face recognition show that, despite the remarkable progress of face recognition models, they are still far behind the human intelligence for perception and recognition. It reveals the vulnerability…

We address the standard quantum error correction using the three-qubit bit-flip code, yet in continuous-time. This entails rendering a target manifold of quantum states globally attractive. Previous feedback designs could feature spurious…

An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake; these perturbations are often invisible or subtle to human observers and highlight vulnerabilities in a model's ability to…