RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

1 code implementation • NeurIPS 2023 • Zhuoqun Huang, Neil G. Marchant, Keane Lucas, Lujo Bauer, Olga Ohrimenko, Benjamin I. P. Rubinstein

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.

Binary Classification Malware Detection

Hard to Forget: Poisoning Attacks on Certified Machine Unlearning

1 code implementation • 17 Sep 2021 • Neil G. Marchant, Benjamin I. P. Rubinstein, Scott Alfeld

The right to erasure requires removal of a user's information from data held by organizations, with rigorous interpretations extending to downstream products such as learned models.

Machine Unlearning

Needle in a Haystack: Label-Efficient Evaluation under Extreme Class Imbalance

2 code implementations • 12 Jun 2020 • Neil G. Marchant, Benjamin I. P. Rubinstein

Important tasks like record linkage and extreme classification demonstrate extreme class imbalance, with 1 minority instance to every 1 million or more majority instances.

d-blink: Distributed End-to-End Bayesian Entity Resolution

4 code implementations • 13 Sep 2019 • Neil G. Marchant, Andee Kaplan, Daniel N. Elazar, Benjamin I. P. Rubinstein, Rebecca C. Steorts

Entity resolution (ER; also known as record linkage or de-duplication) is the process of merging noisy databases, often in the absence of unique identifiers.

Blocking

In Search of an Entity Resolution OASIS: Optimal Asymptotic Sequential Importance Sampling

1 code implementation • 2 Mar 2017 • Neil G. Marchant, Benjamin I. P. Rubinstein

Entity resolution (ER) presents unique challenges for evaluation methodology.

Entity Resolution