Related papers: Confidence-Ranked Reconstruction of Census Microda…

The goal of trace reconstruction is to reconstruct an unknown $n$-bit string $x$ given only independent random traces of $x$, where a random trace of $x$ is obtained by passing $x$ through a deletion channel. A Statistical Query (SQ)…

Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy. Unfortunately, recent works show FL algorithms are vulnerable to the serious data reconstruction attacks. However, existing works lack…

Ratio statistics--such as relative risk and odds ratios--play a central role in hypothesis testing, model evaluation, and decision-making across many areas of machine learning, including causal inference and fairness analysis. However,…

Consider the task of locating an unknown target point using approximate distance queries: in each round, a reconstructor selects a query point and receives a noisy version of its distance to the target. This problem arises naturally in…

Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…

Differential privacy provides a strong form of privacy and allows preserving most of the original characteristics of the dataset. Utilizing these benefits requires one to design specific differentially private data analysis algorithms. In…

Generative models producing synthetic data are meant to provide a privacy-friendly approach to releasing data. However, their privacy guarantees are only considered robust when models satisfy Differential Privacy (DP). Alas, this is not a…

The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and the cloud to reduce latency and protect user privacy.…

The vast majority of network datasets contains errors and omissions, although this is rarely incorporated in traditional network analysis. Recently, an increasing effort has been made to fill this methodological gap by developing network…

Training a deep architecture using a ranking loss has become standard for the person re-identification task. Increasingly, these deep architectures include additional components that leverage part detections, attribute predictions, pose…

We present a comprehensive analysis of privacy attacks and countermeasures in data-driven systems. We systematically categorize attacks targeting three domains: anonymous data (linkage and structural attacks), statistical aggregates…

Randomized response, as a basic building-block for differentially private mechanism, has given rise to great interest and found various potential applications in science communities. In this work, we are concerned with three-elements…

Collaborative inference has recently emerged as an attractive framework for applying deep learning to Internet of Things (IoT) applications by splitting a DNN model into several subpart models among resource-constrained IoT devices and the…

Understanding when and how much a model gradient leaks information about the training sample is an important question in privacy. In this paper, we present a surprising result: even without training or memorizing the data, we can fully…

We demonstrate the feasibility of database reconstruction under a cache side-channel attack on SQLite. Specifically, we present a Flush+Reload attack on SQLite that obtains approximate (or "noisy") volumes of range queries made to a private…

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

We propose and study a multi-scale approach to vector quantization. We develop an algorithm, dubbed reconstruction trees, inspired by decision trees. Here the objective is parsimonious reconstruction of unsupervised data, rather than…

It is important to study the risks of publishing privacy-sensitive data. Even if sensitive identities (e.g., name, social security number) were removed and advanced data perturbation techniques were applied, several de-anonymization attacks…

While person Re-identification (Re-ID) has progressed rapidly due to its wide real-world applications, it also causes severe risks of leaking personal information from training data. Thus, this paper focuses on quantifying this risk by…

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…