23 citations · 74 across the 32 of their papers we have counts for
9 papers · 1 filter
Information bottleneck through variational glasses
Slava Voloshynovskiy, Mouad Kondah, Shideh Rezaeifar +3
Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variatio…
-VAE: Autoregressive parametrization of the VAE encoder
Sohrab Ferdowsi, Maurits Diephuis, Shideh Rezaeifar +1
We make a minimal, but very effective alteration to the VAE model. This is about a drop-in replacement for the (sample-dependent) approximate posterior to change it from the standa…
Single-Component Privacy Guarantees in Helper Data Systems and Sparse Coding with Ambiguation
Behrooz Razeghi, Taras Stanko, Boris Škorić +1
We investigate the privacy of two approaches to (biometric) template protection: Helper Data Systems and Sparse Ternary Coding with Ambiguization. In particular, we focus on a priv…
Robustification of deep net classifiers by key based diversified aggregation with pre-filtering
Olga Taran, Shideh Rezaeifar, Taras Holotyak +1
In this paper, we address a problem of machine learning system vulnerability to adversarial attacks. We propose and investigate a Key based Diversified Aggregation (KDA) mechanism…
Reconstruction of Privacy-Sensitive Data from Protected Templates
Shideh Rezaeifar, Behrooz Razeghi, Olga Taran +2
In this paper, we address the problem of data reconstruction from privacy-protected templates, based on recent concept of sparse ternary coding with ambiguization (STCA). The STCA…
Defending against adversarial attacks by randomized diversification
Olga Taran, Shideh Rezaeifar, Taras Holotyak +1
The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications. In this paper, we propose a randomized diversification as a defense…