Publications (9)
Friend or Faux: Graph-Based Early Detection of Fake Accounts on Social Networks
Adam Breuer, Roee Eilat, Udi Weinsberg
In this paper, we study the problem of early detection of fake user accounts on social networks based solely on their network connectivity with other users. Removing such accounts…
E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time
Adam Breuer
In this paper, we provide the first practical algorithms with provable guarantees for the problem of inferring the topics assigned to each document in an LDA topic model. This is t…
Causal Inference with Video Features as Treatments
Kentaro Nakamura, Adam Breuer, Michael H. Crespin +2
We develop the first statistical methodology for causal inference with video features as treatments. Video is the most engaging content modality on the internet. A central causal q…
Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures
Sayanton V. Dibbo, Adam Breuer, Juston Moore +1
Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private and potentially sensitive training data by repeatedly querying the network. In…
Reducing information dependency does not cause training data privacy. Adversarially non-robust features do
Rasmus Torp, Shailen K. Smith, Adam Breuer
The paper shows that training data privacy against model inversion attacks is not due to memorization but to the presence of non‑robust adversarial features, and introduces a train…
Non-monotone Submodular Maximization in Exponentially Fewer Iterations
Eric Balkanski, Adam Breuer, Yaron Singer
In this paper we consider parallelization for applications whose objective can be expressed as maximizing a non-monotone submodular function under a cardinality constraint. Our mai…