Related papers: Enhanced Membership Inference Attacks against Mach…
As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection between the distinguishability of the training and testing…
With the extensive use of machine learning technologies, data providers encounter increasing privacy risks. Recent legislation, such as GDPR, obligates organizations to remove requested data and its influence from a trained model. Machine…
Auditing mechanisms for differential privacy use probabilistic means to empirically estimate the privacy level of an algorithm. For private machine learning, existing auditing mechanisms are tight: the empirical privacy estimate (nearly)…
The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies,…
We consider the problem of a training data proof, where a data creator or owner wants to demonstrate to a third party that some machine learning model was trained on their data. Training data proofs play a key role in recent lawsuits…
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…
Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model's training data, remain…
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…
Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by observing the prediction output of the ML model. While the key…
Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing data leakage. However, many current state-of-the-art attacks require access to models'…
Large Language Models (LLMs) are prone to memorizing training data, which poses serious privacy risks. Two of the most prominent concerns are training data extraction and Membership Inference Attacks (MIAs). Prior research has shown that…
The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a…
As machine learning (ML) technologies become more prevalent in privacy-sensitive areas like healthcare and finance, eventually incorporating sensitive information in building data-driven algorithms, it is vital to scrutinize whether these…
The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One such privacy risk is Membership Inference (MI), in which an…
Machine learning models are vulnerable to membership inference attack, which can be used to determine whether a given sample appears in the training data. Most existing methods assume the attacker has full access to the features of the…
Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…
Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data scientists and machine learning engineers seek to use…
Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…
Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property $T$ that is unknown when an instruction is issued, and becomes knowable only after the…
We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be vulnerable to membership-inference attacks even when the service provider and users are…