相关论文: Black-box Backdoor Defense via Zero-shot Image Pur…

Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Our paper presents a novel defence against black box attacks, where attackers use the victim model as an oracle to craft their adversarial examples. Unlike traditional preprocessing defences that rely on sanitizing input samples, our…

Diffusion models (DMs) are regarded as one of the most advanced generative models today, yet recent studies suggest that they are vulnerable to backdoor attacks, which establish hidden associations between particular input patterns and…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Recent works have demonstrated that deep learning models are vulnerable to backdoor poisoning attacks, where these attacks instill spurious correlations to external trigger patterns or objects (e.g., stickers, sunglasses, etc.). We find…

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…

Model quantization is a promising approach to compress deep neural networks and accelerate inference, making it possible to be deployed on mobile and edge devices. To retain the high performance of full-precision models, most existing…

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

In this paper, we propose a novel defensive transformation that enables us to maintain a high classification accuracy under the use of both clean images and adversarial examples for adversarially robust defense. The proposed transformation…

We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training…

The vulnerability of face recognition systems to presentation attacks has limited their application in security-critical scenarios. Automatic methods of detecting such malicious attempts are essential for the safe use of facial recognition…

Classifiers based on deep neural networks are susceptible to adversarial attack, where the widely existing vulnerability has invoked the research in defending them from potential threats. Given a vulnerable classifier, existing defense…

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…

Diffusion models have achieved remarkable success in imaging inverse problems owing to their powerful generative capabilities. However, existing approaches typically rely on models trained for specific degradation types, limiting their…

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the lack of data auditing for untrusted clients, FL is…

Real-world backdoor attacks often require poisoned datasets to be stored and transmitted before being used to compromise deep learning systems. However, in the era of big data, the inevitable use of lossy compression poses a fundamental…

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…