Search Results for author:
Found 14 papers, 5 papers with code
Information Leakage from Data Updates in Machine Learning Models
We validate that two snapshots of the model can result in higher information leakage in comparison to having access to only the updated model.
Fingerprint Attack: Client De-Anonymization in Federated Learning
Federated Learning allows collaborative training without data sharing in settings where participants do not trust the central server and one another.
RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion
When applied to the popular MalConv malware detection model, our smoothing mechanism RS-Del achieves a certified accuracy of 91% at an edit distance radius of 128 bytes.
DDoD: Dual Denial of Decision Attacks on Human-AI Teams
Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient.
Verifiable and Provably Secure Machine Unlearning
In this framework, the server first computes a proof that the model was trained on a dataset $D$.
Protecting Global Properties of Datasets with Distribution Privacy Mechanisms
In this work, we demonstrate how a distribution privacy framework can be applied to formalize such data confidentiality.
Oblivious Sampling Algorithms for Private Data Analysis
We study secure and privacy-preserving data analysis based on queries executed on samples from a dataset.
Attribute Privacy: Framework and Mechanisms
We propose definitions to capture \emph{attribute privacy} in two relevant cases where global attributes may need to be protected: (1) properties of a specific dataset and (2) parameters of the underlying distribution from which dataset is sampled.
Replication-Robust Payoff-Allocation for Machine Learning Data Markets
In this paper, we systematically study the replication manipulation in submodular games and investigate replication robustness, a metric that quantitatively measures the robustness of solution concepts against replication.
Leakage of Dataset Properties in Multi-Party Machine Learning
Using multiple machine learning models, we show that leakage occurs even if the sensitive attribute is not included in the training data and has a low correlation with other attributes or the target variable.
Analyzing Information Leakage of Updates to Natural Language Models
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models.
Collaborative Machine Learning Markets with Data-Replication-Robust Payments
We study the problem of collaborative machine learning markets where multiple parties can achieve improved performance on their machine learning tasks by combining their training data.
Analyzing Privacy Loss in Updates of Natural Language Models
To continuously improve quality and reflect changes in data, machine learning-based services have to regularly re-train and update their core models.
Contamination Attacks and Mitigation in Multi-Party Machine Learning
Machine learning is data hungry; the more data a model has access to in training, the more likely it is to perform well at inference time.
