Search
Search Results
-
Imperceptible and multi-channel backdoor attack
Recent researches demonstrate that Deep Neural Networks (DNN) models are vulnerable to backdoor attacks. The backdoored DNN model will behave...
-
Enhanced Coalescence Backdoor Attack Against DNN Based on Pixel Gradient
Deep learning has been widely used in many applications such as face recognition, autonomous driving, etc. However, deep learning models are...
-
Compression-resistant backdoor attack against deep neural networks
In recent years, a number of backdoor attacks against deep neural networks (DNN) have been proposed. In this paper, we reveal that backdoor attacks...
-
Active poisoning: efficient backdoor attacks on transfer learning-based brain-computer interfaces
Transfer learning (TL) has been widely used in electroencephalogram (EEG)-based brain-computer interfaces (BCIs) for reducing calibration efforts....
-
Invisible backdoor learning in regional transform domain
The rapid develo** deep learning is highly required by resources and computing resources, which easily leads to backdoor learnings. It is difficult...
-
NBA: defensive distillation for backdoor removal via neural behavior alignment
Recently, deep neural networks have been shown to be vulnerable to backdoor attacks. A backdoor is inserted into neural networks via this attack...
-
A stealthy and robust backdoor attack via frequency domain transform
Deep learning models are vulnerable to backdoor attacks, where an adversary aims to inject a hidden backdoor into the deep learning models, such that...
-
DLP: towards active defense against backdoor attacks with decoupled learning process
Deep learning models are well known to be susceptible to backdoor attack, where the attacker only needs to provide a tampered dataset on which the...
-
Backdoor Attacks against Learning-Based Algorithms
This book introduces a new type of data poisoning attack, dubbed, backdoor attack. In backdoor attacks, an attacker can train the model with poisoned... -
Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-level Backdoor Attacks
The pre-training-then-fine-tuning paradigm has been widely used in deep learning. Due to the huge computation cost for pre-training, practitioners...
-
Black-Box Graph Backdoor Defense
Recently, graph neural networks (GNNs) have been proven to be vulnerable to backdoor attacks, wherein the test prediction of the model is manipulated... -
Literature Review of Backdoor Attacks
In this chapter, we first introduce three application areas of deep neural networks, including computer vision, natural language processing, and... -
Backdoor Attacks and Defense in FL
Federated Learning (FL) has received significant interest from both the research field and industry perspective. One of the most promising cross-silo... -
Backdoor Attack on Dynamic Link Prediction
Based on historical information, graph prediction is performed by Dynamic Link Prediction (DLP). The quality of the training data plays a crucial... -
TRGE: A Backdoor Detection After Quantization
Quantization is evolving as the main technique for efficient deployment of deep neural networks to hardware devices, especially edge devices.... -
Backdoor Attacks Leveraging Latent Representation in Competitive Learning
Backdoor attacks on machine learning are attacks where an adversary obtains the expected output for a particular input called a trigger, and a... -
Evil vs evil: using adversarial examples to against backdoor attack in federated learning
As a distributed learning paradigm, federated learning (FL) has shown great success in aggregating information from different clients to train a...
-
Distributed Backdoor Attacks in Federated Learning Generated by DynamicTriggers
The emergence of federated learning has alleviated the dual challenges of data silos and data privacy and security in machine learning. However, this... -
BadDet: Backdoor Attacks on Object Detection
Backdoor attack is a severe security threat which injects a backdoor trigger into a small portion of training data such that the trained model gives... -
DFaP: Data Filtering and Purification Against Backdoor Attacks
The rapid development of deep learning has led to a dramatic increase in user demand for training data. As a result, users are often compelled to...