Search Results for author:
Found 17 papers, 11 papers with code
Multi-Constraint Safe RL with Objective Suppression for Safety-Critical Applications
Safe reinforcement learning tasks with multiple constraints are a challenging domain despite being very common in the real world.
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions.
Smoothed Embeddings for Certified Few-Shot Learning
In this work, we extend randomized smoothing to few-shot learning models that map inputs to normalized embeddings.
Many Heads but One Brain: Fusion Brain -- a Competition and a Single Multimodal Multitask Architecture
Supporting the current trend in the AI community, we present the AI Journey 2021 Challenge called Fusion Brain, the first competition which is targeted to make the universal architecture which could process different modalities (in this case, images, texts, and code) and solve multiple tasks for vision and language.
CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks
In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks -- small modifications of the input that change the predictions.
Manifold Hypothesis in Data Analysis: Double Geometrically-Probabilistic Approach to Manifold Dimension Estimation
The probabilistic method is new.
Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations
Currently the most popular method of providing robustness certificates is randomized smoothing where an input is smoothed via some probability distribution.
Darker than Black-Box: Face Reconstruction from Similarity Queries
Several methods for inversion of face recognition models were recently presented, attempting to reconstruct a face from deep templates.
MDMMT: Multidomain Multimodal Transformer for Video Retrieval
We present a new state-of-the-art on the text to video retrieval task on MSRVTT and LSMDC benchmarks where our model outperforms all previous solutions by a large margin.
Ranked #25 on
Video Retrieval
on LSMDC
(using extra training data)
Quadric Hypersurface Intersection for Manifold Learning in Feature Space
The knowledge that data lies close to a particular submanifold of the ambient Euclidean space may be useful in a number of ways.
Robustness Threats of Differential Privacy
Differential privacy (DP) is a gold-standard concept of measuring and guaranteeing privacy in data analysis.
Mutual Modality Learning for Video Action Classification
In this paper, we explore the various methods to embed the ensemble power into a single model.
Ranked #47 on
Action Recognition
on Something-Something V2
(using extra training data)
Black-Box Face Recovery from Identity Features
In this work, we present a novel algorithm based on an it-erative sampling of random Gaussian blobs for black-box face recovery, given only an output feature vector of deep face recognition systems.
Geometry-Inspired Top-k Adversarial Perturbations
The brittleness of deep image classifiers to small adversarial input perturbations has been extensively studied in the last several years.
On adversarial patches: real-world attack on ArcFace-100 face recognition system
We examine security of one of the best public face recognition systems, LResNet100E-IR with ArcFace loss, and propose a simple method to attack it in the physical world.
Real-world adversarial attack on MTCNN face detection system
Recent studies proved that deep learning approaches achieve remarkable results on face detection task.
AdvHat: Real-world adversarial attack on ArcFace Face ID system
In this paper we propose a novel easily reproducible technique to attack the best public Face ID system ArcFace in different shooting conditions.
