scholarly journals Modelling cryptographic distinguishers using machine learning

2021 ◽  
Author(s):  
Carlo Brunetta ◽  
Pablo Picazo-Sanchez
Keyword(s):  
Machine Learning ◽  
Empirical Evidence ◽  
Blind Spot ◽  
Cryptographic Primitives ◽  
Basic Approach

AbstractCryptanalysis is the development and study of attacks against cryptographic primitives and protocols. Many cryptographic properties rely on the difficulty of generating an adversary who, given an object sampled from one of two classes, correctly distinguishes the class used to generate that object. In the case of cipher suite distinguishing problem, the classes are two different cryptographic primitives. In this paper, we propose a methodology based on machine learning to automatically generate classifiers that can be used by an adversary to solve any distinguishing problem. We discuss the assumptions, a basic approach for improving the advantage of the adversary as well as a phenomenon that we call the “blind spot paradox”. We apply our methodology to generate distinguishers for the NIST (DRBG) cipher suite problem. Finally, we provide empirical evidence that the distinguishers might statistically have some advantage to distinguish between the DRBG used.

scholarly journals Beneficial and harmful explanatory machine learning

2021 ◽  
Author(s):  
Lun Ai ◽  
Stephen H. Muggleton ◽  
Céline Hocquette ◽  
Mark Gromowski ◽  
Ute Schmid
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Beneficial Effect ◽  
Empirical Evidence ◽  
Task Performance ◽  
Human Performance ◽  
Human Learning ◽  
Science Literature ◽  
Definition Of ◽  
Self Learning

AbstractGiven the recent successes of Deep Learning in AI there has been increased interest in the role and need for explanations in machine learned theories. A distinct notion in this context is that of Michie’s definition of ultra-strong machine learning (USML). USML is demonstrated by a measurable increase in human performance of a task following provision to the human of a symbolic machine learned theory for task performance. A recent paper demonstrates the beneficial effect of a machine learned logic theory for a classification task, yet no existing work to our knowledge has examined the potential harmfulness of machine’s involvement for human comprehension during learning. This paper investigates the explanatory effects of a machine learned theory in the context of simple two person games and proposes a framework for identifying the harmfulness of machine explanations based on the Cognitive Science literature. The approach involves a cognitive window consisting of two quantifiable bounds and it is supported by empirical evidence collected from human trials. Our quantitative and qualitative results indicate that human learning aided by a symbolic machine learned theory which satisfies a cognitive window has achieved significantly higher performance than human self learning. Results also demonstrate that human learning aided by a symbolic machine learned theory that fails to satisfy this window leads to significantly worse performance than unaided human learning.

The Role of Data Analytics and Machine Learning in Resurrecting Inductive-Based Accounting Research

2021 ◽  
Vol 9 (2) ◽  
pp. 1-19
Author(s):  
Lawrence A. Gordon
Keyword(s):  
Machine Learning ◽  
Empirical Evidence ◽  
Data Analytics ◽  
Accounting Research ◽  
Recent Developments ◽  
Important Trend ◽  
The Impact ◽  
The Way

The objective of this paper is to assess the impact of data analytics (DA) and machine learning (ML) on accounting research.[1] As discussed in the paper, the inherent inductive nature of DA and ML is creating an important trend in the way accounting research is being conducted. That trend is the increasing utilization of inductive-based research among accounting researchers. Indeed, as a result of the recent developments with DA and ML, a rebalancing is taking place between inductive-based and deductive-based research in accounting.[2] In essence, we are witnessing the resurrection of inductive-based accounting research. A brief review of some empirical evidence to support the above argument is also provided in the paper.   

scholarly journals Ensemble modeling approach for rainfall/groundwater balancing

2007 ◽  
Vol 9 (2) ◽  
pp. 95-106 ◽  
Author(s):  
D. Laucelli ◽  
O. Giustolisi ◽  
V. Babovic ◽  
M. Keijzer
Keyword(s):  
Machine Learning ◽  
Genetic Programming ◽  
Empirical Evidence ◽  
Averaging Method ◽  
Total Error ◽  
Ensemble Methods ◽  
Real Data ◽  
Symbolic Regression ◽  
Ensemble Modeling ◽  
Physical Phenomena

This paper introduces an application of machine learning, on real data. It deals with Ensemble Modeling, a simple averaging method for obtaining more reliable approximations using symbolic regression. Considerations on the contribution of bias and variance to the total error, and ensemble methods to reduce errors due to variance, have been tackled together with a specific application of ensemble modeling to hydrological forecasts. This work provides empirical evidence that genetic programming can greatly benefit from this approach in forecasting and simulating physical phenomena. Further considerations have been taken into account, such as the influence of Genetic Programming parameter settings on the model's performance.

scholarly journals How Does Knowledge of the AUC Constrain the Set of Possible Ground-Truth Labelings?

2019 ◽  
Vol 33 ◽  
pp. 5425-5432
Author(s):  
Jacob Whitehill
Keyword(s):  
Machine Learning ◽  
Empirical Evidence ◽  
Recent Work ◽  
Roc Curve ◽  
Binary Classification ◽  
Ground Truth ◽  
Mathematical Structure ◽  
Test Set ◽  
Classification Tasks ◽  
N Vector

Recent work on privacy-preserving machine learning has considered how datamining competitions such as Kaggle could potentially be “hacked”, either intentionally or inadvertently, by using information from an oracle that reports a classifier’s accuracy on the test set (Blum and Hardt 2015; Hardt and Ullman 2014; Zheng 2015; Whitehill 2016). For binary classification tasks in particular, one of the most common accuracy metrics is the Area Under the ROC Curve (AUC), and in this paper we explore the mathematical structure of how the AUC is computed from an n-vector of real-valued “guesses” with respect to the ground-truth labels. Under the assumption of perfect knowledge of the test set AUC c=p/q, we show how knowing c constrains the set W of possible ground-truth labelings, and we derive an algorithm both to compute the exact number of such labelings and to enumerate efficiently over them. We also provide empirical evidence that, surprisingly, the number of compatible labelings can actually decrease as n grows, until a test set-dependent threshold is reached. Finally, we show how W can be efficiently whittled down, through pairs of oracle queries, to infer all the groundtruth test labels with complete certainty.

scholarly journals Fingerprint Distortion Detection

2020 ◽  
pp. 559-562
Author(s):  
Harshada Kanade ◽  
Gauri Uttarwar ◽  
Shweta Borse ◽  
Archana. K
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
User Authentication ◽  
Efficient Algorithms ◽  
Biometric Recognition ◽  
Cryptographic Primitives ◽  
Security Systems ◽  
Detection Systems

Fingerprint is widely used in biometrics, for identification of individual’s identity. Biometric recognition is a leading technology for identification and security systems. It has unique identification among all other biometric modalities. Most anomaly detection systems rely upon machine learning. Calculations are performed to identify suspicious occasion. The primary purpose of this system is to ensure a reliable and accurate user authentication; this study addresses the problem of developing accurate, generalizable, and efficient algorithms for detecting fingerprint spoof attacks. The approach is to utilize local patches centered and aligned using fingerprint details. That proposed approach is to provide accuracies in fingerprint spoof detection for intra-sensor, cross material, crosssensor, as well as cross-dataset testing scenarios. The principle used is similar to the working of some cryptographic primitives, in particular to present the key into the plan so that a couple of operations are infeasible without knowing it.

scholarly journals What do RL Models Measure? Interpreting Model Parameters in Cognition and Neuroscience

2021 ◽  
Author(s):  
Maria Eckstein ◽  
Linda Wilbrecht ◽  
Anne Collins
Keyword(s):  
Machine Learning ◽  
Reinforcement Learning ◽  
Cognitive Science ◽  
Empirical Evidence ◽  
Cognitive Processes ◽  
Future Research ◽  
Model Parameters ◽  
Research Needs ◽  
Research Fields ◽  
Computational Research

Reinforcement learning (RL) is a concept that has been invaluable to research fields including machine learning, neuroscience, and cognitive science. However, what RL entails partly differs between fields, leading to difficulties when interpreting and translating findings.This paper lays out these differences and zooms in on cognitive (neuro)science, revealing that we often overinterpret RL modeling results, with severe consequences for future research. Specifically, researchers often assume---implicitly---that model parameters \textit{generalize} between tasks, models, and participant populations, despite overwhelming negative empirical evidence for this assumption. We also often assume that parameters measure specific, unique, and meaningful (neuro)cognitive processes, a concept we call \textit{interpretability}, for which empirical evidence is also lacking. We conclude that future computational research needs to pay increased attention to these implicit assumptions when using RL models, and suggest an alternative framework that resolves these issues and allows us to unleash the potential of RL in cognitive (neuro)science.

scholarly journals A survey on feature weighting based K-Means algorithms

2020 ◽  
Author(s):  
Renato Cordeiro de Amorim
Keyword(s):  
Machine Learning ◽  
Empirical Evidence ◽  
Real World ◽  
Clustering Algorithm ◽  
Machine Learning Algorithms ◽  
Feature Weighting ◽  
Future Research ◽  
Real World Data ◽  
Data Set ◽  
Partitional Clustering

In a real-world data set there is always the possibility, rather high in our opinion, that different features may have different degrees of relevance. Most machine learning algorithms deal with this fact by either selecting or deselecting features in the data preprocessing phase. However, we maintain that even among relevant features there may be different degrees of relevance, and this should be taken into account during the clustering process. With over 50 years of history, K-Means is arguably the most popular partitional clustering algorithm there is. The first K-Means based clustering algorithm to compute feature weights was designed just over 30 years ago. Various such algorithms have been designed since but there has not been, to our knowledge, a survey integrating empirical evidence of cluster recovery ability, common flaws, and possible directions for future research. This paper elaborates on the concept of feature weighting and addresses these issues by critically analysing some of the most popular, or innovative, feature weighting mechanisms based in K-Means

Visual Tactics Toward an Ethical Debugging

2018 ◽  
Vol 4 (1) ◽  
pp. 217-226
Author(s):  
Catherine Griffiths
Keyword(s):  
Machine Learning ◽  
Job Performance ◽  
Interaction Design ◽  
Design Research ◽  
Blind Spot ◽  
Black Box ◽  
Machine Learning Algorithms ◽  
Critical Study ◽  
Intelligent Algorithms ◽  
Ethical Implications

Abstract To advance design research into a critical study of artificially intelligent algorithms, strategies from the fields of critical code studies and data visualisation are combined to propose a methodology for computational visualisation. By opening the algorithmic black box to think through the meaning created by structure and process, computational visualisation seeks to elucidate the complexity and obfuscation at the heart of artificial intelligence systems. There are rising ethical dilemmas that are a consequence of the use of machine learning algorithms in socially sensitive spaces, such as in determining criminal sentencing, job performance, or access to welfare. This is in part due to the lack of a theoretical framework to understand how and why decisions are made at the algorithmic level. The ethical implications are becoming more severe as such algorithmic decision-making is being given higher authority while there is a simultaneous blind spot in where and how biases arise. Computational visualisation, as a method, explores how contemporary visual design tactics including generative design and interaction design, can intersect with a critical exegesis of algorithms to challenge the black box and obfuscation of machine learning and work toward an ethical debugging of biases in such systems.

Sign in / Sign up

Export Citation Format

Share Document