Related papers: Auditing Membership Leakages of Multi-Exit Network…

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer…

We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample…

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

As AI agents are increasingly adopted to collaborate on complex objectives, ensuring the security of autonomous multi-agent systems becomes crucial. We develop simulations of agents collaborating on shared objectives to study these security…

Federated Learning enables entities to collaboratively learn a shared prediction model while keeping their training data locally. It prevents data collection and aggregation and, therefore, mitigates the associated privacy risks. However,…

Early-exit networks are effective solutions for reducing the overall energy consumption and latency of deep learning models by adjusting computation based on the complexity of input data. By incorporating intermediate exit branches into the…

Federated learning enables training high-utility models across several clients without directly sharing their private data. As a downside, the federated setting makes the model vulnerable to various adversarial attacks in the presence of…

Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of analgorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist forDP training algorithms. However machine…

Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy…

The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis,…

The smart grid is envisioned to significantly enhance the efficiency of energy consumption, by utilizing two-way communication channels between consumers and operators. For example, operators can opportunistically leverage the delay…

Communication bottleneck and data privacy are two critical concerns in federated multi-armed bandit (MAB) problems, such as situations in decision-making and recommendations of connected vehicles via wireless. In this paper, we design the…

Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely on identifying and…

This paper exploits the potential of physical layer security in massive multiple-input multiple-output (MIMO) aided two-tier heterogeneous networks (HetNets). We focus on the downlink secure transmission in the presence of multiple…

As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed…

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…

In a biometric authentication or identification system, the matcher compares a stored and a fresh template to determine whether there is a match. This assessment is based on both a similarity score and a predefined threshold. For better…

Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inference Attacks (MIAs), where adversaries aim to infer…

Federated learning has emerged as a promising paradigm for collaborative model training while preserving data privacy. However, recent studies have shown that it is vulnerable to various privacy attacks, such as data reconstruction attacks.…

Machine unlearning (MU) has emerged as a key mechanism for ensuring data privacy and regulatory compliance by enabling models to forget specific training samples. However, recent studies have shown that the removal of data can inadvertently…