Related papers: Confidence Is All You Need for MI Attacks
Malicious adversaries can attack machine learning models to infer sensitive information or damage the system by launching a series of evasion attacks. Although various work addresses privacy and security concerns, they focus on individual…
In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Specifically, membership attack aims…
Property inference attacks reveal statistical properties about a training set but are difficult to distinguish from the primary purposes of statistical machine learning, which is to produce models that capture statistical properties about a…
There is a known tension between the need to analyze personal data to drive business and privacy concerns. Many data protection regulations, including the EU General Data Protection Regulation (GDPR) and the California Consumer Protection…
Membership inference attacks (MIA) aim to infer whether a particular data point is part of the training dataset of a model. In this paper, we propose a new task in the context of LLM privacy: entity-level discovery of membership risk…
Training Data Detection (TDD) is a task aimed at determining whether a specific data instance is used to train a machine learning model. In the computer security literature, TDD is also referred to as Membership Inference Attack (MIA).…
In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases,…
Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…
It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…
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…
Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task.…
Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…
Federated Learning (FL) enables collaborative model training while keeping training data localized, allowing us to preserve privacy in various domains including remote sensing. However, recent studies show that FL models may still leak…
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…
Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition. The image encoder pre-trained through MIM, involving the masking and subsequent reconstruction of input…
Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the…
In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. However, recent work shows that client's private information…
Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for…
The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Meanwhile, users often have limited control over whether their…
A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of…