相关论文: Physical Invisible Backdoor Based on Camera Imagin…

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…

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Federated learning, an innovative network architecture designed to safeguard user privacy, is gaining widespread adoption in the realm of technology. However, given the existence of backdoor attacks in federated learning, exploring the…

This work explores an emerging security threat against deep neural networks (DNNs) based image classification, i.e., backdoor attack. In this scenario, the attacker aims to inject a backdoor into the model by manipulating training data,…

Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive learning, MIM attains state-of-the-art performance by masking…

Backdoor attacks in machine learning have drawn significant attention for their potential to compromise models stealthily, yet most research has focused on homogeneous data such as images. In this work, we propose a novel backdoor attack on…

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data and perceive the environment. However, DNN models are vulnerable to different types of adversarial attacks, which pose significant risks to the…

Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network activated when the trigger is added to its input. In most works…

In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models. However, many existing approaches require substantial…

Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data. The attacked model behaves normally on benign samples, whereas its prediction will be…

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Accurate face recognition techniques make a series of critical applications possible: policemen could employ it to retrieve criminals' faces from surveillance video streams; cross boarder travelers could pass a face authentication…

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers…

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to…

Prompt-driven Video Segmentation Foundation Models (VSFMs), such as SAM2, are increasingly used in applications including autonomous driving and digital pathology, yet their security risks remain underexplored. We study backdoor attacks…

Personal devices (e.g. laptops, tablets, and mobile phones) are conventional in daily life and have the ability to store users' private data. The security problems related to these appliances have become a primary concern for both users and…

Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be easily countered by…

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Recently, a backdoor data poisoning attack was proposed, which adds mislabeled examples to the training set, with an embedded backdoor pattern, aiming to have the classifier learn to classify to a target class whenever the backdoor pattern…