Related papers: Analysis and Detectability of Offline Data Poisoni…
While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements…
Federated learning (FL) is an emerging paradigm for distributed training of large-scale deep neural networks in which participants' data remains on their own devices with only model updates being shared with a central server. However, the…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Large amounts of incremental learning algorithms have been proposed to alleviate the catastrophic forgetting issue arises while dealing with sequential data on a time series. However, the adversarial robustness of incremental learners has…
Many machine learning systems rely on data collected in the wild from untrusted sources, exposing the learning algorithms to data poisoning. Attackers can inject malicious data in the training dataset to subvert the learning process,…
Manipulation of local training data and local updates, i.e., the poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Most existing poisoning attacks aim to manipulate local…
Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…
Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned…
With the growing adoption of AI and machine learning systems in real-world applications, ensuring their fairness has become increasingly critical. The majority of the work in algorithmic fairness focus on assessing and improving the…
This paper studies physical consequences of unobservable false data injection (FDI) attacks designed only with information inside a sub-network of the power system. The goal of this attack is to overload a chosen target line without being…
We show that by controlling parts of a physical environment in which a pre-trained deep neural network (DNN) is being fine-tuned online, an adversary can launch subtle data poisoning attacks that degrade the performance of the system. While…
Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…
Artificial intelligence models trained from data can only be as good as the underlying data is. Biases in training data propagating through to the output of a machine learning model are a well-documented and well-understood phenomenon, but…
This paper establishes a mathematically precise definition of dataset poisoning attack and proves that the very act of effectively poisoning a dataset ensures that the attack can be effectively detected. On top of a mathematical guarantee…
The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…
A class of data integrity attack, known as false data injection (FDI) attack, has been studied with a considerable amount of work. It has shown that with perfect knowledge of the system model and the capability to manipulate a certain…
Learned index structures achieve high performance by modeling the cumulative distribution function (CDF) of keys, but this reliance on data distributions introduces potential vulnerability to adversarial manipulation. Prior work has…
Federated edge learning can be essential in supporting privacy-preserving, artificial intelligence (AI)-enabled activities in digital twin 6G-enabled Internet of Things (IoT) environments. However, we need to also consider the potential of…
Imperceptible poisoning attacks on entire datasets have recently been touted as methods for protecting data privacy. However, among a number of defenses preventing the practical use of these techniques, early-stopping stands out as a…
While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to develop a…