Related papers: Mitigating the ICA Attack against Rotation Based T…

Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GIAs), which recover…

Large language models (LLMs) have been widely applied for their remarkable capability of content generation. However, the practical use of open-source LLMs is hindered by high resource requirements, making deployment expensive and limiting…

The current literature on memorization in Natural Language Models, especially Large Language Models (LLMs), poses severe security and privacy risks, as models tend to memorize personally identifying information (PIIs) from training data. We…

To preserve client privacy in the data mining process, a variety of techniques based on random perturbation of data records have been proposed recently. In this paper, we present a generalized matrix-theoretic model of random perturbation,…

With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years. However, most of them cannot be put into production due to their slow training and inference speed caused by…

Randomized controlled trials (RCTs) have become powerful tools for assessing the impact of interventions and policies in many contexts. They are considered the gold standard for causal inference in the biomedical fields and many social…

One of the key advantages of Federated Learning (FL) is its ability to collaboratively train a Machine Learning (ML) model while keeping clients' data on-site. However, this can create a false sense of security. Despite not sharing private…

Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse of facial data. Existing adversarial privacy protection methods rely on input-space…

The proliferation of propaganda on mobile platforms raises critical concerns around detection accuracy and user privacy. To address this, we propose TRIDENT - a three-tier propaganda detection model implementing transformers, adversarial…

The gold standard for privacy in machine learning, Differential Privacy (DP), is often interpreted through its guarantees against membership inference. However, translating DP budgets into quantitative protection against the more damaging…

Large language models (LLMs) are increasingly deployed in interactive and retrieval-augmented settings, raising significant privacy concerns. While attacks such as Membership Inference (MIA), Attribute Inference (AIA), Data Extraction…

Search for the optimizer in computationally demanding model predictive control (MPC) setups can be facilitated by Cloud as a service provider in cyber-physical systems. This advantage introduces the risk that Cloud can obtain unauthorized…

Sequential Recommenders, which exploit dynamic user intents through interaction sequences, is vulnerable to adversarial attacks. While existing attacks primarily rely on data poisoning, they require large-scale user access or fake profiles…

Authentication systems are vulnerable to model inversion attacks where an adversary is able to approximate the inverse of a target machine learning model. Biometric models are a prime candidate for this type of attack. This is because…

The increased availability of genetic data has transformed genomics research, but raised many privacy concerns regarding its handling due to its sensitive nature. This work explores the use of language models (LMs) for the generation of…

Modern machine learning systems increasingly rely on sensitive data, creating significant privacy, security, and regulatory risks that existing privacy-preserving machine learning (ppML) techniques, such as Differential Privacy (DP) and…

Membership Inference Attacks (MIAs) pose a significant privacy risk by enabling adversaries to determine if a specific data point was part of a model's training set. This work empirically investigates whether MU algorithms can function as a…

Privacy Preserving Data Mining(PPDM) is an ongoing research area aimed at bridging the gap between the collaborative data mining and data confidentiality There are many different approaches which have been adopted for PPDM, of them the rule…

Differential privacy (DP) offers strong theoretical privacy guarantees, but implementations of DP mechanisms may be vulnerable to side-channel attacks, such as timing attacks. When sampling methods such as MCMC or rejection sampling are…

The increasing need for sharing healthcare data and collaborating on clinical research has raised privacy concerns. Health information leakage due to malicious attacks can lead to serious problems such as misdiagnoses and patient…