相关论文: Single Image Backdoor Inversion via Robust Smoothe…

Clean-image backdoor attacks, which use only label manipulation in training datasets to compromise deep neural networks, pose a significant threat to security-critical applications. A critical flaw in existing methods is that the poison…

Backdoor attack has been considered as a serious security threat to deep neural networks (DNNs). Poisoned sample detection (PSD) that aims at filtering out poisoned samples from an untrustworthy training dataset has shown very promising…

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…

Deep Neural Networks (DNN) are becoming increasingly more important in assisted and automated driving. Using such entities which are obtained using machine learning is inevitable: tasks such as recognizing traffic signs cannot be developed…

Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows attackers to control the model to misclassify poisoned…

Diffusion models have achieved notable success in image generation, but they remain highly vulnerable to backdoor attacks, which compromise their integrity by producing specific undesirable outputs when presented with a pre-defined trigger.…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack…

Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers. However, methods based on RS require augmenting data with large amounts of noise, which leads to…

Recent studies show that despite achieving high accuracy on a number of real-world applications, deep neural networks (DNNs) can be backdoored: by injecting triggered data samples into the training dataset, the adversary can mislead the…

This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected stage of the machine learning pipeline, the attack surfaces…

Backdoor learning is a critical research topic for understanding the vulnerabilities of deep neural networks. While the diffusion model (DM) has been broadly deployed in public over the past few years, the understanding of its backdoor…

Federated learning (FL) allows a set of agents to collaboratively train a model without sharing their potentially sensitive data. This makes FL suitable for privacy-preserving applications. At the same time, FL is susceptible to adversarial…

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

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…

Backdoor data poisoning attacks have recently been demonstrated in computer vision research as a potential safety risk for machine learning (ML) systems. Traditional data poisoning attacks manipulate training data to induce unreliability of…

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…

Underwater image restoration attracts significant attention due to its importance in unveiling the underwater world. This paper elaborates on a novel method that achieves state-of-the-art results for underwater image restoration based on…

In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given model weights and the corresponding gradients. We introduce…

Split learning is a collaborative learning design that allows several participants (clients) to train a shared model while keeping their datasets private. Recent studies demonstrate that collaborative learning models, specifically federated…