Related papers: A Data-Driven Defense against Edge-case Model Pois…
Federated learning (FL) has been widely deployed to enable machine learning training on sensitive data across distributed devices. However, the decentralized learning paradigm and heterogeneity of FL further extend the attack surface for…
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…
Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic…
Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of…
Most machine learning applications rely on centralized learning processes, opening up the risk of exposure of their training datasets. While federated learning (FL) mitigates to some extent these privacy risks, it relies on a trusted…
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…
A powerful category of (invisible) data poisoning attacks modify a subset of training examples by small adversarial perturbations to change the prediction of certain test-time data. Existing defense mechanisms are not desirable to deploy in…
Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…
There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact…
Federated learning (FL) enables multiple clients to train a model without compromising sensitive data. The decentralized nature of FL makes it susceptible to adversarial attacks, especially backdoor insertion during training. Recently, the…
Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…
Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is…
In big data era, machine learning is one of fundamental techniques in intrusion detection systems (IDSs). However, practical IDSs generally update their decision module by feeding new data then retraining learning models in a periodical…
Deep neural networks are susceptible to poisoning attacks by purposely polluted training data with specific triggers. As existing episodes mainly focused on attack success rate with patch-based samples, defense algorithms can easily detect…
The growing reliance of intelligent systems on data makes the systems vulnerable to data poisoning attacks. Such attacks could compromise machine learning or deep learning models by disrupting the input data. Previous studies on data…
Deep neural networks (DNNs) are recently shown to be vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by injecting a few poisoned examples into the training dataset. While extensive efforts have been…
In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks…
We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to…
The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…
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,…