Related papers: Improved Certified Defenses against Data Poisoning…
Federated learning (FL) enables privacy-preserving collaborative model training but remains vulnerable to adversarial behaviors that compromise model utility or fairness across sensitive groups. While extensive studies have examined attacks…
Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vulnerable to backdoor attacks, which inject a shared backdoor…
Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense mechanisms have made notable progress, they fail to protect…
Federated learning (FL) combined with local differential privacy (LDP) enables privacy-preserving model training across decentralized data sources. However, the decentralized data-management paradigm leaves LDPFL vulnerable to participants…
Federated learning (FL) is gaining increasing attention as an emerging collaborative machine learning approach, particularly in the context of large-scale computing and data systems. However, the fundamental algorithm of FL, Federated…
Federated Learning (FL) is a distributed learning paradigm designed to address privacy concerns. However, FL is vulnerable to poisoning attacks, where Byzantine clients compromise the integrity of the global model by submitting malicious…
Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we…
Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support samples) for a classification task. However, an attacker could…
Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks. In this study, our focus is on backdoor attacks in which the adversary's goal is to…
Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification of an unmodified test image and as such breach model…
Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…
In this paper, we address a problem of machine learning system vulnerability to adversarial attacks. We propose and investigate a Key based Diversified Aggregation (KDA) mechanism as a defense strategy. The KDA assumes that the attacker (i)…
With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…
Federated Learning (FL) is a paradigm in Machine Learning (ML) that addresses data privacy, security, access rights and access to heterogeneous information issues by training a global model using distributed nodes. Despite its advantages,…
Neural networks are susceptible to data inference attacks such as the model inversion attack and the membership inference attack, where the attacker could infer the reconstruction and the membership of a data sample from the confidence…
The performance of machine learning models depends on the quality of the underlying data. Malicious actors can attack the model by poisoning the training data. Current detectors are tied to either specific data types, models, or attacks,…
Federated learning has a variety of applications in multiple domains by utilizing private training data stored on different devices. However, the aggregation process in federated learning is highly vulnerable to adversarial attacks so that…
We study the membership inference (MI) attack against classifiers, where the attacker's goal is to determine whether a data instance was used for training the classifier. Through systematic cataloging of existing MI attacks and extensive…
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…
Conformal prediction provides model-agnostic and distribution-free uncertainty quantification through prediction sets that are guaranteed to include the ground truth with any user-specified probability. Yet, conformal prediction is not…