scholarly journals Ulixes: Facial Recognition Privacy with Adversarial Machine Learning

2021 ◽  
Vol 2022 (1) ◽  
pp. 148-165
Author(s):  
Thomas Cilloni ◽  
Wei Wang ◽  
Charles Walter ◽  
Charles Fleming
Keyword(s):  
Machine Learning ◽  
State Of The Art ◽  
Facial Recognition ◽  
Clustering Methods ◽  
Non Invasive ◽  
Current State ◽  
Social Media Platforms ◽  
Adversarial Examples ◽  
The Cost ◽  
Photo Management

Abstract Facial recognition tools are becoming exceptionally accurate in identifying people from images. However, this comes at the cost of privacy for users of online services with photo management (e.g. social media platforms). Particularly troubling is the ability to leverage unsupervised learning to recognize faces even when the user has not labeled their images. In this paper we propose Ulixes, a strategy to generate visually non-invasive facial noise masks that yield adversarial examples, preventing the formation of identifiable user clusters in the embedding space of facial encoders. This is applicable even when a user is unmasked and labeled images are available online. We demonstrate the effectiveness of Ulixes by showing that various classification and clustering methods cannot reliably label the adversarial examples we generate. We also study the effects of Ulixes in various black-box settings and compare it to the current state of the art in adversarial machine learning. Finally, we challenge the effectiveness of Ulixes against adversarially trained models and show that it is robust to countermeasures.

scholarly journals Evolutionary Machine Learning for Multi-Objective Class Solutions in Medical Deformable Image Registration

Algorithms ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 99 ◽  
Author(s):  
Kleopatra Pirpinia ◽  
Peter A. N. Bosman ◽  
Jan-Jakob Sonke ◽  
Marcel van Herk ◽  
Tanja Alderliesten
Keyword(s):  
Machine Learning ◽  
Image Registration ◽  
State Of The Art ◽  
Deformable Image Registration ◽  
Optimization Approach ◽  
High Quality ◽  
Trade Off ◽  
Multi Objective ◽  
Current State ◽  
Image Artefacts

Current state-of-the-art medical deformable image registration (DIR) methods optimize a weighted sum of key objectives of interest. Having a pre-determined weight combination that leads to high-quality results for any instance of a specific DIR problem (i.e., a class solution) would facilitate clinical application of DIR. However, such a combination can vary widely for each instance and is currently often manually determined. A multi-objective optimization approach for DIR removes the need for manual tuning, providing a set of high-quality trade-off solutions. Here, we investigate machine learning for a multi-objective class solution, i.e., not a single weight combination, but a set thereof, that, when used on any instance of a specific DIR problem, approximates such a set of trade-off solutions. To this end, we employed a multi-objective evolutionary algorithm to learn sets of weight combinations for three breast DIR problems of increasing difficulty: 10 prone-prone cases, 4 prone-supine cases with limited deformations and 6 prone-supine cases with larger deformations and image artefacts. Clinically-acceptable results were obtained for the first two problems. Therefore, for DIR problems with limited deformations, a multi-objective class solution can be machine learned and used to compute straightforwardly multiple high-quality DIR outcomes, potentially leading to more efficient use of DIR in clinical practice.

Computing Robust Principal Components by A* Search

2018 ◽  
Vol 27 (07) ◽  
pp. 1860013 ◽  
Author(s):  
Swair Shah ◽  
Baokun He ◽  
Crystal Maung ◽  
Haim Schweitzer
Keyword(s):  
State Of The Art ◽  
Principal Component ◽  
Low Rank ◽  
A Algorithm ◽  
Running Time ◽  
Current State ◽  
Dimensionality Reduction Technique ◽  
Related Variant ◽  
Low Rank Representation ◽  
The Cost

Principal Component Analysis (PCA) is a classical dimensionality reduction technique that computes a low rank representation of the data. Recent studies have shown how to compute this low rank representation from most of the data, excluding a small amount of outlier data. We show how to convert this problem into graph search, and describe an algorithm that solves this problem optimally by applying a variant of the A* algorithm to search for the outliers. The results obtained by our algorithm are optimal in terms of accuracy, and are shown to be more accurate than results obtained by the current state-of-the- art algorithms which are shown not to be optimal. This comes at the cost of running time, which is typically slower than the current state of the art. We also describe a related variant of the A* algorithm that runs much faster than the optimal variant and produces a solution that is guaranteed to be near the optimal. This variant is shown experimentally to be more accurate than the current state-of-the-art and has a comparable running time.

scholarly journals Detecting Emotions in English and Arabic Tweets

Information ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 98 ◽  
Author(s):  
Tariq Ahmad ◽  
Allan Ramsay ◽  
Hanady Ahmed
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Learning Algorithms ◽  
General Purpose ◽  
Machine Learning Algorithms ◽  
Current State ◽  
Optimal Thresholds ◽  
Alternative Approach

Assigning sentiment labels to documents is, at first sight, a standard multi-label classification task. Many approaches have been used for this task, but the current state-of-the-art solutions use deep neural networks (DNNs). As such, it seems likely that standard machine learning algorithms, such as these, will provide an effective approach. We describe an alternative approach, involving the use of probabilities to construct a weighted lexicon of sentiment terms, then modifying the lexicon and calculating optimal thresholds for each class. We show that this approach outperforms the use of DNNs and other standard algorithms. We believe that DNNs are not a universal panacea and that paying attention to the nature of the data that you are trying to learn from can be more important than trying out ever more powerful general purpose machine learning algorithms.

scholarly journals A Review of the State of the Art in Non-Contact Sensing for COVID-19

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5665
Author(s):  
William Taylor ◽  
Qammer H. Abbasi ◽  
Kia Dashtipour ◽  
Shuja Ansari ◽  
Syed Aziz Shah ◽  
...  
Keyword(s):  
Healthcare Workers ◽  
State Of The Art ◽  
Future Research ◽  
Research Directions ◽  
Advantages And Disadvantages ◽  
Non Invasive ◽  
Current State ◽  
Global Pandemic ◽  
Future Research Directions ◽  
Contact Sensing

COVID-19, caused by SARS-CoV-2, has resulted in a global pandemic recently. With no approved vaccination or treatment, governments around the world have issued guidance to their citizens to remain at home in efforts to control the spread of the disease. The goal of controlling the spread of the virus is to prevent strain on hospitals. In this paper, we focus on how non-invasive methods are being used to detect COVID-19 and assist healthcare workers in caring for COVID-19 patients. Early detection of COVID-19 can allow for early isolation to prevent further spread. This study outlines the advantages and disadvantages and a breakdown of the methods applied in the current state-of-the-art approaches. In addition, the paper highlights some future research directions, which need to be explored further to produce innovative technologies to control this pandemic.

scholarly journals Solution of Levinthal’s Paradox and a Physical Theory of Protein Folding Times

Biomolecules ◽  
2020 ◽  
Vol 10 (2) ◽  
pp. 250
Author(s):  
Dmitry N. Ivankov ◽  
Alexei V. Finkelstein
Keyword(s):  
Machine Learning ◽  
Free Energy ◽  
Protein Folding ◽  
Physical Theory ◽  
State Of The Art ◽  
Energy Minimum ◽  
Folding Kinetics ◽  
Reasonable Time ◽  
Current State ◽  
Conceptual Aspect

“How do proteins fold?” Researchers have been studying different aspects of this question for more than 50 years. The most conceptual aspect of the problem is how protein can find the global free energy minimum in a biologically reasonable time, without exhaustive enumeration of all possible conformations, the so-called “Levinthal’s paradox.” Less conceptual but still critical are aspects about factors defining folding times of particular proteins and about perspectives of machine learning for their prediction. We will discuss in this review the key ideas and discoveries leading to the current understanding of folding kinetics, including the solution of Levinthal’s paradox, as well as the current state of the art in the prediction of protein folding times.

scholarly journals Generating Adversarial Examples for Holding Robustness of Source Code Processing Models

2020 ◽  
Vol 34 (01) ◽  
pp. 1169-1176
Author(s):  
Huangzhao Zhang ◽  
Zhuo Li ◽  
Ge Li ◽  
Lei Ma ◽  
Yang Liu ◽  
...  
Keyword(s):  
Programming Languages ◽  
State Of The Art ◽  
Source Code ◽  
Natural Languages ◽  
Current State ◽  
Automated Processing ◽  
Adversarial Examples ◽  
Adversarial Training ◽  
New Challenges ◽  
And Performance

Automated processing, analysis, and generation of source code are among the key activities in software and system lifecycle. To this end, while deep learning (DL) exhibits a certain level of capability in handling these tasks, the current state-of-the-art DL models still suffer from non-robust issues and can be easily fooled by adversarial attacks.Different from adversarial attacks for image, audio, and natural languages, the structured nature of programming languages brings new challenges. In this paper, we propose a Metropolis-Hastings sampling-based identifier renaming technique, named \fullmethod (\method), which generates adversarial examples for DL models specialized for source code processing. Our in-depth evaluation on a functionality classification benchmark demonstrates the effectiveness of \method in generating adversarial examples of source code. The higher robustness and performance enhanced through our adversarial training with \method further confirms the usefulness of DL models-based method for future fully automated source code processing.

scholarly journals Cost-Based Goal Recognition in Navigational Domains

2019 ◽  
Vol 64 ◽  
pp. 197-242 ◽  
Author(s):  
Peta Masters ◽  
Sebastian Sardina
Keyword(s):  
State Of The Art ◽  
Identical Result ◽  
Task Planning ◽  
Maximum Probability ◽  
Current State ◽  
Current Location ◽  
Starting Point ◽  
Goal Recognition ◽  
The Cost ◽  
Start Location

Goal recognition is the problem of determining an agent's intent by observing her behaviour. Contemporary solutions for general task-planning relate the probability of a goal to the cost of reaching it. We adapt this approach to goal recognition in the strict context of path-planning. We show (1) that a simpler formula provides an identical result to current state-of-the-art in less than half the time under all but one set of conditions. Further, we prove (2) that the probability distribution based on this technique is independent of an agent's past behaviour and present a revised formula that achieves goal recognition by reference to the agent's starting point and current location only. Building on this, we demonstrate (3) that a Radius of Maximum Probability (i.e., the distance from a goal within which that goal is guaranteed to be the most probable) can be calculated from relative cost-distances between the candidate goals and a start location, without needing to calculate any actual probabilities. In this extended version of earlier work, we generalise our framework to the continuous domain and discuss our results, including the conditions under which our findings can be generalised back to goal recognition in general task-planning.

scholarly journals Carbapenems: A Short Review about their Current Status

2021 ◽  
Vol 04 (01) ◽  
Author(s):  
Syeda Warda Zahra ◽  
Keyword(s):  
Cost Effectiveness ◽  
State Of The Art ◽  
Short Review ◽  
Current Status ◽  
Clinical Use ◽  
Beta Lactams ◽  
Beta Lactamases ◽  
Current State ◽  
The Cost

In this review, we summarize the current “state of the art” of carbapenem antibiotics and their role in our antimicrobial armamentarium. Among the beta-lactams currently available, carbapenems are unique because they are relatively resistant to hydrolysis by most beta-lactamases. Herein, we described the cost effectiveness, safety, and advantages of carbapenems as compared to other antibiotics. We also highlight important features of the carbapenems that are presently in clinical use: imipenem-cilastatin, meropenem, ertapenem, doripenem, panipenem-betamipron, and biapenem. In closing, we emphasize some major challenges related to oral formulatuion of carbapenems and different strategies to overcome these challenges.

scholarly journals Rapid discovery of novel prophages using biological feature engineering and machine learning

2020 ◽  
Author(s):  
Kimmo Sirén ◽  
Andrew Millard ◽  
Bent Petersen ◽  
M Thomas P Gilbert ◽  
Martha RJ Clokie ◽  
...  
Keyword(s):  
Machine Learning ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Feature Space ◽  
Machine Learning Method ◽  
Biological Feature ◽  
Bacterial Genomes ◽  
Current State ◽  
Starting Point ◽  
Feature Based

ABSTRACTProphages are phages that are integrated into bacterial genomes and which are key to understanding many aspects of bacterial biology. Their extreme diversity means they are challenging to detect using sequence similarity, yet this remains the paradigm and thus many phages remain unidentified. We present a novel, fast and generalizing machine learning method based on feature space to facilitate novel prophage discovery. To validate the approach, we reanalyzed publicly available marine viromes and single-cell genomes using our feature-based approaches and found consistently more phages than were detected using current state-of-the-art tools while being notably faster. This demonstrates that our approach significantly enhances bacteriophage discovery and thus provides a new starting point for exploring new biologies.

Automatic Detection of Emotion in Music

2009 ◽  
pp. 9-33 ◽  
Author(s):  
Cyril Laurier ◽  
Perfecto Herrera
Keyword(s):  
Machine Learning ◽  
State Of The Art ◽  
Automatic Detection ◽  
Machine Learning Method ◽  
Future Trends ◽  
Learning Method ◽  
Proof Of Concept ◽  
Current State ◽  
Emotions In Music

Creating emotionally sensitive machines will significantly enhance the interaction between humans and machines. In this chapter we focus on enabling this ability for music. Music is extremely powerful to induce emotions. If machines can somehow apprehend emotions in music, it gives them a relevant competence to communicate with humans. In this chapter we review the theories of music and emotions. We detail different representations of musical emotions from the literature, together with related musical features. Then, we focus on techniques to detect the emotion in music from audio content. As a proof of concept, we detail a machine learning method to build such a system. We also review the current state of the art results, provide evaluations and give some insights into the possible applications and future trends of these techniques.

Sign in / Sign up

Export Citation Format

Share Document