Related papers: Secure Confidential Business Information When Shar…
Deploying machine learning (ML) in dynamic data-driven applications systems (DDDAS) can improve the security of industrial control systems (ICS). However, ML-based DDDAS are vulnerable to adversarial attacks because adversaries can alter…
Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns. On one hand, potential gains are highly anticipated if different organizations…
In this survey, we will explore the interaction between secure multiparty computation and the area of machine learning. Recent advances in secure multiparty computation (MPC) have significantly improved its applicability in the realm of…
Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent…
Security has always been a critical issue in machine learning (ML) applications. Due to the high cost of model training -- such as collecting relevant samples, labeling data, and consuming computing power -- model-stealing attack is one of…
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…
Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive server-client communication gives room for backdoor attacks with…
Increasing use of ML technologies in privacy-sensitive domains such as medical diagnoses, lifestyle predictions, and business decisions highlights the need to better understand if these ML technologies are introducing leakages of sensitive…
LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These…
Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the federated learning…
The performance of deep learning models highly depends on the amount of training data. It is common practice for today's data holders to merge their datasets and train models collaboratively, which yet poses a threat to data privacy.…
Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning…
Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more…
Model Extraction Attacks (MEAs) threaten modern machine learning systems by enabling adversaries to steal models, exposing intellectual property and training data. With the increasing deployment of machine learning models in distributed…
Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a serious security risk. Progress in defending these models…
The growing cybersecurity threats make it essential to use high-quality data to train Machine Learning (ML) models for network traffic analysis, without noisy or missing data. By selecting the most relevant features for cyber-attack…
When used in automated decision-making systems, machine learning (ML) models are vulnerable to data-manipulation attacks. Some defense mechanisms (e.g., adversarial regularization) directly affect the ML models while others (e.g., anomaly…
Designing cyber defense systems to account for cognitive biases in human decision making has demonstrated significant success in improving performance against human attackers. However, much of the attention in this area has focused on…
Modern machine learning models are increasingly deployed behind APIs. This renders standard weight-privatization methods (e.g. DP-SGD) unnecessarily noisy at the cost of utility. While model weights may vary significantly across training…