Dimensionality reduction as a defense against evasion attacks on machine learning classifiers
|
|
- Chloe Holmes
- 6 years ago
- Views:
Transcription
1 Dimensionality reduction as a defense against evasion attacks on machine learning classifiers Arjun Nitin Bhagoji and Prateek Mittal Princeton University DC-Area Anonymity, Privacy, and Security Seminar, Fall
2 The Sixfold Path 1. Motivation 2. Machine learning, briefly 3. Adversaries and attacks 4. Defenses 5. Results 6. Ongoing Work and Extensions 2
3 Motivation 3
4 The The Ubiquity Ubiquity of of Machine Machine Learning learning Images Malware Machine Learning Systems Sound SVMs, Neural Networks, Random Forests, Cat Dog Malicious Benign Who are you? Open mail 4
5 Critical Applications of ML 5
6 Vulnerability of ML Modified by adversary Classified as 5 Classified as 0 Figure taken from Explaining and harnessing adversarial examples by Goodfellow et. al. 6
7 Machine Learning, Briefly 7
8 Typical ML Pipeline Training phase Training Data Labels Training data Training algorithm 1. Starts with f 0,untrained classifier 2. Optimizes to find f, which labels most data correctly Test phase Test Data Labels Trained ML Classifier y = f(x) Verify Test data Predicted labels 8 To find misclassification percentage
9 Support Vector Machines (SVMs) Support vectors Linear SVM on UCI Human Activity Recognition dataset Sitting vs. Walking Margin: Distance between parallel hyperplanes separating data Maximum margin separating hyperplane Image courtesy: Wikimedia Foundation Max. margin hyperplane: Halfway in between parallel hyperplanes 9
10 Adversaries and Attacks 10
11 Adversarial setup During the test phase (or once deployed) Trained ML Classifier y = f(x) x adv y adv = f(x adv ) y adv? = y Minimally modifies legitimate inputs to induce misclassification at test time Assume powerful adversary: has knowledge of trained classifier and input datasets Previous work has shown black-box ML systems can be reverse engineered enough to carry out evasion attacks using queries 11
12 Evasion Attack on Linear SVM x Classified as 7 Adversarial Class Original Class x adv Classified as 3! x adv = x w k. kw k k 2 Adversarial image with =2.0. Leads to 100% misclassification on test set. 2 [0, 1) Attack on Linear SVMs controls the amount of perturbation added (typically small) 12
13 Not just Images Images Szegedy et. al. (2014), Papernot et. al. (2015) Xu et. al. (2016) Malware Machine Learning Systems Sound SVMs, Neural Networks, Random Forests, Cat Malicious Dog Benign Who are you? Open mail Carlini et. al. (2016) 13
14 Defenses 14
15 Defense Desiderata Add defense here and/or modify the classifier x adv Trained ML Classifier y = f(x) y def = f def (x def ) y def = y Maintain classification accuracy (utility) Low efficiency overhead Improve security, i.e. resistance to adversarial samples Tunable, i.e. tradeoff utility, efficiency and security Effective in a range of settings 15
16 Limitations of Existing Defenses Focused on specific classifier families Resistance to adversary with knowledge of defense is unclear Only valid for specific attacks Case in point Proposed defense for neural networks of Papernot et. al. (2015) broken by modified attack in Carlini et. al. (2016) 16
17 Dimensionality reduction Preprocessing step for high-dimensional data Novel use as a defense against evasion attacks Various Algorithms tried Principal Component Analysis (PCA) Random Projections Kernel PCA 17
18 Principal Component Analysis d k u i : 1 n XT X u i = i u i k n d n Data Principal Components Reduced Dimension Data Principal component Use Principal Component Analysis (PCA) to reduce dimension Identifies top k directions of highest variance Directions: eigenvectors of covariance matrix 18
19 Reconstruction-based defense Step 1: Compute ˆx =, reconstructed input kx hx, u i iu i i=1 Initial adversarial example (Input may be benign or adversarial) Step 2: Find f(ˆx), where f( ) is the original classifier After reconstruction Intuition Perturbation added in existing attacks has low variance Reconstruction step removes perturbation 19
20 Re-training based defense f k Step 1: Train new classifier on (red. dim. training data) X train k Step 2: Project all inputs to k dimensions Step 3: Use f k to classify subsequent inputs Intuition For SVMs, margin increases for lower-dimensional classifiers 20
21 Results 21
22 Validation of defenses Do the defenses work for 1. different datasets? 2. various ML classifiers? 3. different attacks on the same classifier? 4. dimensionality reduction algorithms other than PCA? 22
23 Datasets used MNIST: Handwritten digits from 0 to 9. Extensively studied from the attack perspective. Enables visual evaluation of defenses. UCI HAR: Measurements obtained from a smartphone's accelerometer and gyroscope. Six activities: Walking, Walking Upstairs, Walking Downstairs, Sitting, Standing and Laying. 23
24 Linear SVM: Re-training Defense for MNIST Reconstruction 92.33% No defense 9.43% =0 24
25 Linear SVM: Reconstruction Defense for HAR 77.88% 28.74% 25
26 Classification accuracy HAR dataset 96.7% MNIST dataset 91.5% 91.2% 91.6% Takeaway: Defenses work for two different datasets with minimal utility loss 26
27 Neural Network: Reconstruction Defense for MNIST 96.86%, Utility: 97.71% 33.77%, Utility: 96.43% Re-training gives 7.17% misclassification at utility of 97.19%! 27
28 Ongoing Work and Extensions 28
29 Strategic attacks What if the adversary is aware of the defenses? For PCA defense, heuristically, adversary adds perturbation in directions with large projection along principal components Ongoing evaluations suggest defenses are effective even for strategic adversary 29
30 Extensions Formal definitions of classifier security Proofs for the effectiveness of dimensionality reduction Optimal attacks against various defenses and classifiers 30
31 That s all folks! Questions? 31
32 Backup slides 32
33 Evasion Attack on Neural Networks Classified as 5 Fast Sign Gradient attack x adv = x + sign(rj f (x,y, )) 2 [0, 1] Classified as 0! where J f ( ) is the loss function of the neural network Adversarial image with =0.15 Leads to 99% misclassification on test set. 33
34 Neural Networks p 1 p p 3 p C Input layer Output softmax layer Hidden layers Function that takes an input x and outputs a vector of probabilities y, giving the probability of each class 34
35 Motivation Machine Learning systems are ubiquitous BUT Vulnerable to adversarially modified inputs SO Good defenses are needed 35
36 Dimensionality reduction as a defense against evasion attacks on machine learning classifiers min r krk 2 subject to f(x + r) =l, Classified as 8 x + r 2 [0, 1] d. x re is the input, perturbation, r and Classified as 3 neural network. f 36
37 Linear SVM: Re-training Defense for MNIST 37
38 Linear SVM: Reconstruction Defense for Reconstruction MNIST 92.33% No defense 10.39% =0 38
39 Linear SVM: Re-training defense for HAR 39
Vulnerability of machine learning models to adversarial examples
Vulnerability of machine learning models to adversarial examples Petra Vidnerová Institute of Computer Science The Czech Academy of Sciences Hora Informaticae 1 Outline Introduction Works on adversarial
More informationAdversarial Attacks on Image Recognition*
Adversarial Attacks on Image Recognition* Masha Itkina, Yu Wu, and Bahman Bahmani 3 Abstract This project extends the work done by Papernot et al. in [4] on adversarial attacks in image recognition. We
More informationCountering Adversarial Images using Input Transformations
Countering Adversarial Images using Input Transformations Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens Van Der Maaten Presented by Hari Venugopalan, Zainul Abi Din Motivation: Why is this a hard problem
More informationProperties of adv 1 Adversarials of Adversarials
Properties of adv 1 Adversarials of Adversarials Nils Worzyk and Oliver Kramer University of Oldenburg - Dept. of Computing Science Oldenburg - Germany Abstract. Neural networks are very successful in
More informationCSC 411: Lecture 14: Principal Components Analysis & Autoencoders
CSC 411: Lecture 14: Principal Components Analysis & Autoencoders Raquel Urtasun & Rich Zemel University of Toronto Nov 4, 2015 Urtasun & Zemel (UofT) CSC 411: 14-PCA & Autoencoders Nov 4, 2015 1 / 18
More informationCSC 411: Lecture 14: Principal Components Analysis & Autoencoders
CSC 411: Lecture 14: Principal Components Analysis & Autoencoders Richard Zemel, Raquel Urtasun and Sanja Fidler University of Toronto Zemel, Urtasun, Fidler (UofT) CSC 411: 14-PCA & Autoencoders 1 / 18
More informationAdversarial Machine Learning An Introduction. With slides from: Binghui Wang
Adversarial Machine Learning An Introduction With slides from: Binghui Wang Outline Machine Learning (ML) Adversarial ML Attack Taxonomy Capability Adversarial Training Conclusion Outline Machine Learning
More informationAI AND CYBERSECURITY APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN SECURITY UNDERSTANDING AND DEFENDING AGAINST ADVERSARIAL AI
SESSION ID: SPO2-T07 AI AND CYBERSECURITY APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN SECURITY UNDERSTANDING AND DEFENDING AGAINST ADVERSARIAL AI Sridhar Muppidi IBM Fellow and VP Technology IBM Security
More informationCS570: Introduction to Data Mining
CS570: Introduction to Data Mining Classification Advanced Reading: Chapter 8 & 9 Han, Chapters 4 & 5 Tan Anca Doloc-Mihu, Ph.D. Slides courtesy of Li Xiong, Ph.D., 2011 Han, Kamber & Pei. Data Mining.
More informationAdversarial Examples in Deep Learning. Cho-Jui Hsieh Computer Science & Statistics UC Davis
Adversarial Examples in Deep Learning Cho-Jui Hsieh Computer Science & Statistics UC Davis Adversarial Example Adversarial Example More Examples Robustness is critical in real systems More Examples Robustness
More informationAdversarial Examples and Adversarial Training. Ian Goodfellow, Staff Research Scientist, Google Brain CS 231n, Stanford University,
Adversarial Examples and Adversarial Training Ian Goodfellow, Staff Research Scientist, Google Brain CS 231n, Stanford University, 2017-05-30 Overview What are adversarial examples? Why do they happen?
More informationCS 229 Midterm Review
CS 229 Midterm Review Course Staff Fall 2018 11/2/2018 Outline Today: SVMs Kernels Tree Ensembles EM Algorithm / Mixture Models [ Focus on building intuition, less so on solving specific problems. Ask
More informationarxiv: v4 [cs.cr] 19 Mar 2017
arxiv:1602.02697v4 [cs.cr] 19 Mar 2017 Practical Black-Box Attacks against Machine Learning Nicolas Papernot Patrick McDaniel Pennsylvania State University ngp5056@cse.psu.edu Pennsylvania State University
More informationData Mining: Concepts and Techniques. Chapter 9 Classification: Support Vector Machines. Support Vector Machines (SVMs)
Data Mining: Concepts and Techniques Chapter 9 Classification: Support Vector Machines 1 Support Vector Machines (SVMs) SVMs are a set of related supervised learning methods used for classification Based
More informationTutorial on Machine Learning Tools
Tutorial on Machine Learning Tools Yanbing Xue Milos Hauskrecht Why do we need these tools? Widely deployed classical models No need to code from scratch Easy-to-use GUI Outline Matlab Apps Weka 3 UI TensorFlow
More informationarxiv: v1 [cs.cr] 1 Aug 2017
ADVERSARIAL-PLAYGROUND: A Visualization Suite Showing How Adversarial Examples Fool Deep Learning Andrew P. Norton * Yanjun Qi Department of Computer Science, University of Virginia arxiv:1708.00807v1
More informationarxiv: v2 [cs.cr] 19 Feb 2016
arxiv:1602.02697v2 [cs.cr] 19 Feb 2016 Practical Black-Box Attacks against Deep Learning Systems using Adversarial Examples Nicolas Papernot - The Pennsylvania State University Patrick McDaniel - The Pennsylvania
More informationNeural Networks and Deep Learning
Neural Networks and Deep Learning Example Learning Problem Example Learning Problem Celebrity Faces in the Wild Machine Learning Pipeline Raw data Feature extract. Feature computation Inference: prediction,
More informationarxiv: v3 [cs.cr] 31 May 2018
DARTS: Deceiving Autonomous Cars with Toxic Signs Chawin Sitawarin Princeton University Princeton, NJ, USA Arjun Nitin Bhagoji Princeton University Princeton, NJ, USA Arsalan Mosenia Princeton University
More informationECE 285 Class Project Report
ECE 285 Class Project Report Based on Source localization in an ocean waveguide using supervised machine learning Yiwen Gong ( yig122@eng.ucsd.edu), Yu Chai( yuc385@eng.ucsd.edu ), Yifeng Bu( ybu@eng.ucsd.edu
More informationData Science Bootcamp Curriculum. NYC Data Science Academy
Data Science Bootcamp Curriculum NYC Data Science Academy 100+ hours free, self-paced online course. Access to part-time in-person courses hosted at NYC campus Machine Learning with R and Python Foundations
More informationCapsule Networks. Eric Mintun
Capsule Networks Eric Mintun Motivation An improvement* to regular Convolutional Neural Networks. Two goals: Replace max-pooling operation with something more intuitive. Keep more info about an activated
More informationOn Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions
On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions CAMCOS Report Day December 9th, 2015 San Jose State University Project Theme: Classification The Kaggle Competition
More informationCAMCOS Report Day. December 9 th, 2015 San Jose State University Project Theme: Classification
CAMCOS Report Day December 9 th, 2015 San Jose State University Project Theme: Classification On Classification: An Empirical Study of Existing Algorithms based on two Kaggle Competitions Team 1 Team 2
More informationFishy Faces: Crafting Adversarial Images to Poison Face Authentication
Fishy Faces: Crafting Adversarial Images to Poison Face Authentication Giuseppe Garofalo, Vera Rimmer, Tim Van hamme, Davy Preuveneers and Wouter Joosen WOOT 2018, August 13-14 (Baltimore, MD, USA) Face
More informationHuman Activity Recognition via Cellphone Sensor Data
Human Activity Recognition via Cellphone Sensor Data Wei Ji, Heguang Liu, Jonathan Fisher Abstract The purpose of this project is to identify human activities while using cell phones via mobile sensor
More informationLECTURE 5: DUAL PROBLEMS AND KERNELS. * Most of the slides in this lecture are from
LECTURE 5: DUAL PROBLEMS AND KERNELS * Most of the slides in this lecture are from http://www.robots.ox.ac.uk/~az/lectures/ml Optimization Loss function Loss functions SVM review PRIMAL-DUAL PROBLEM Max-min
More informationAll lecture slides will be available at CSC2515_Winter15.html
CSC2515 Fall 2015 Introduc3on to Machine Learning Lecture 9: Support Vector Machines All lecture slides will be available at http://www.cs.toronto.edu/~urtasun/courses/csc2515/ CSC2515_Winter15.html Many
More informationSUPPORT VECTOR MACHINES
SUPPORT VECTOR MACHINES Today Reading AIMA 8.9 (SVMs) Goals Finish Backpropagation Support vector machines Backpropagation. Begin with randomly initialized weights 2. Apply the neural network to each training
More informationForgotten Siblings: Unifying Attacks on Machine Learning and Digital Watermarking
Forgotten Siblings: Unifying Attacks on Machine Learning and Digital Watermarking Erwin Quiring, Daniel Arp and Konrad Rieck Technische Universität Braunschweig Brunswick, Germany Abstract Machine learning
More informationPractical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms
Practical Black-box Attacks on Deep Neural Networks using Efficient Query Mechanisms Arjun Nitin Bhagoji 1, Warren He 2, Bo Li 3, and Dawn Song 2 1 Princeton University 2 University of California, Berkeley
More informationShape Context Matching For Efficient OCR
Matching For Efficient OCR May 14, 2012 Matching For Efficient OCR Table of contents 1 Motivation Background 2 What is a? Matching s Simliarity Measure 3 Matching s via Pyramid Matching Matching For Efficient
More informationCIS 520, Machine Learning, Fall 2015: Assignment 7 Due: Mon, Nov 16, :59pm, PDF to Canvas [100 points]
CIS 520, Machine Learning, Fall 2015: Assignment 7 Due: Mon, Nov 16, 2015. 11:59pm, PDF to Canvas [100 points] Instructions. Please write up your responses to the following problems clearly and concisely.
More informationRobot Learning. There are generally three types of robot learning: Learning from data. Learning by demonstration. Reinforcement learning
Robot Learning 1 General Pipeline 1. Data acquisition (e.g., from 3D sensors) 2. Feature extraction and representation construction 3. Robot learning: e.g., classification (recognition) or clustering (knowledge
More informationLecture Linear Support Vector Machines
Lecture 8 In this lecture we return to the task of classification. As seen earlier, examples include spam filters, letter recognition, or text classification. In this lecture we introduce a popular method
More informationKernels + K-Means Introduction to Machine Learning. Matt Gormley Lecture 29 April 25, 2018
10-601 Introduction to Machine Learning Machine Learning Department School of Computer Science Carnegie Mellon University Kernels + K-Means Matt Gormley Lecture 29 April 25, 2018 1 Reminders Homework 8:
More informationSupport Vector Machines + Classification for IR
Support Vector Machines + Classification for IR Pierre Lison University of Oslo, Dep. of Informatics INF3800: Søketeknologi April 30, 2014 Outline of the lecture Recap of last week Support Vector Machines
More informationUnderstanding Adversarial Space through the lens of Attribution
Understanding Adversarial Space through the lens of Attribution Mayank Singh 1 [0000 0001 7261 6347], Nupur Kumari 1 [0000 0003 1799 1069], Abhishek Sinha 1 [0000 0002 3598 480X], and Balaji Krishnamurthy
More information1 Case study of SVM (Rob)
DRAFT a final version will be posted shortly COS 424: Interacting with Data Lecturer: Rob Schapire and David Blei Lecture # 8 Scribe: Indraneel Mukherjee March 1, 2007 In the previous lecture we saw how
More informationTransductive Learning: Motivation, Model, Algorithms
Transductive Learning: Motivation, Model, Algorithms Olivier Bousquet Centre de Mathématiques Appliquées Ecole Polytechnique, FRANCE olivier.bousquet@m4x.org University of New Mexico, January 2002 Goal
More informationTutorials (M. Biehl)
Tutorials 09-11-2018 (M. Biehl) Suggestions: - work in groups (as formed for the other tutorials) - all this should work in the python environments that you have been using; but you may also switch to
More informationRecognizing Handwritten Digits Using the LLE Algorithm with Back Propagation
Recognizing Handwritten Digits Using the LLE Algorithm with Back Propagation Lori Cillo, Attebury Honors Program Dr. Rajan Alex, Mentor West Texas A&M University Canyon, Texas 1 ABSTRACT. This work is
More informationOnline Pose Classification and Walking Speed Estimation using Handheld Devices
Online Pose Classification and Walking Speed Estimation using Handheld Devices Jun-geun Park MIT CSAIL Joint work with: Ami Patel (MIT EECS), Jonathan Ledlie (Nokia Research), Dorothy Curtis (MIT CSAIL),
More informationarxiv: v1 [cs.cv] 27 Dec 2017
Adversarial Patch Tom B. Brown, Dandelion Mané, Aurko Roy, Martín Abadi, Justin Gilmer {tombrown,dandelion,aurkor,abadi,gilmer}@google.com arxiv:1712.09665v1 [cs.cv] 27 Dec 2017 Abstract We present a method
More informationFraud Detection using Machine Learning
Fraud Detection using Machine Learning Aditya Oza - aditya19@stanford.edu Abstract Recent research has shown that machine learning techniques have been applied very effectively to the problem of payments
More informationActivity recognition and energy expenditure estimation
Activity recognition and energy expenditure estimation A practical approach with Python WebValley 2015 Bojan Milosevic Scope Goal: Use wearable sensors to estimate energy expenditure during everyday activities
More informationVulnerability of machine learning models to adversarial examples
ITAT 216 Proceedings, CEUR Workshop Proceedings Vol. 1649, pp. 187 194 http://ceur-ws.org/vol-1649, Series ISSN 1613-73, c 216 P. Vidnerová, R. Neruda Vulnerability of machine learning models to adversarial
More informationInstance-based Learning
Instance-based Learning Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University February 19 th, 2007 2005-2007 Carlos Guestrin 1 Why not just use Linear Regression? 2005-2007 Carlos Guestrin
More informationLecture 19: Generative Adversarial Networks
Lecture 19: Generative Adversarial Networks Roger Grosse 1 Introduction Generative modeling is a type of machine learning where the aim is to model the distribution that a given set of data (e.g. images,
More informationTensor Sparse PCA and Face Recognition: A Novel Approach
Tensor Sparse PCA and Face Recognition: A Novel Approach Loc Tran Laboratoire CHArt EA4004 EPHE-PSL University, France tran0398@umn.edu Linh Tran Ho Chi Minh University of Technology, Vietnam linhtran.ut@gmail.com
More informationFast and Evasive Attacks: Highlighting the Challenges Ahead
Fast and Evasive Attacks: Highlighting the Challenges Ahead Moheeb Rajab, Fabian Monrose, and Andreas Terzis Computer Science Department Johns Hopkins University Outline Background Related Work Sampling
More informationCPSC 340: Machine Learning and Data Mining. More Linear Classifiers Fall 2017
CPSC 340: Machine Learning and Data Mining More Linear Classifiers Fall 2017 Admin Assignment 3: Due Friday of next week. Midterm: Can view your exam during instructor office hours next week, or after
More informationDeep Learning for Embedded Security Evaluation
Deep Learning for Embedded Security Evaluation Emmanuel Prouff 1 1 Laboratoire de Sécurité des Composants, ANSSI, France April 2018, CISCO April 2018, CISCO E. Prouff 1/22 Contents 1. Context and Motivation
More informationCPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2017
CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2017 Assignment 3: 2 late days to hand in tonight. Admin Assignment 4: Due Friday of next week. Last Time: MAP Estimation MAP
More informationHomework 4: Clustering, Recommenders, Dim. Reduction, ML and Graph Mining (due November 19 th, 2014, 2:30pm, in class hard-copy please)
Virginia Tech. Computer Science CS 5614 (Big) Data Management Systems Fall 2014, Prakash Homework 4: Clustering, Recommenders, Dim. Reduction, ML and Graph Mining (due November 19 th, 2014, 2:30pm, in
More informationNeural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing
Neural Networks for unsupervised learning From Principal Components Analysis to Autoencoders to semantic hashing feature 3 PC 3 Beate Sick Many slides are taken form Hinton s great lecture on NN: https://www.coursera.org/course/neuralnets
More informationContent-based image and video analysis. Machine learning
Content-based image and video analysis Machine learning for multimedia retrieval 04.05.2009 What is machine learning? Some problems are very hard to solve by writing a computer program by hand Almost all
More informationDiscriminative classifiers for image recognition
Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study
More information3D Object Recognition using Multiclass SVM-KNN
3D Object Recognition using Multiclass SVM-KNN R. Muralidharan, C. Chandradekar April 29, 2014 Presented by: Tasadduk Chowdhury Problem We address the problem of recognizing 3D objects based on various
More informationBagging for One-Class Learning
Bagging for One-Class Learning David Kamm December 13, 2008 1 Introduction Consider the following outlier detection problem: suppose you are given an unlabeled data set and make the assumptions that one
More informationECE 285 Final Project
ECE 285 Final Project Michael Threet mthreet@ucsd.edu Chenyin Liu chl586@ucsd.edu Rui Guo rug009@eng.ucsd.edu Abstract Source localization allows for range finding in underwater acoustics. Traditionally,
More informationCSE 40171: Artificial Intelligence. Learning from Data: Unsupervised Learning
CSE 40171: Artificial Intelligence Learning from Data: Unsupervised Learning 32 Homework #6 has been released. It is due at 11:59PM on 11/7. 33 CSE Seminar: 11/1 Amy Reibman Purdue University 3:30pm DBART
More informationAn Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation
An Empirical Evaluation of Deep Architectures on Problems with Many Factors of Variation Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, and Yoshua Bengio Université de Montréal 13/06/2007
More informationSupport vector machines
Support vector machines When the data is linearly separable, which of the many possible solutions should we prefer? SVM criterion: maximize the margin, or distance between the hyperplane and the closest
More informationArtificial Neural Networks (Feedforward Nets)
Artificial Neural Networks (Feedforward Nets) y w 03-1 w 13 y 1 w 23 y 2 w 01 w 21 w 22 w 02-1 w 11 w 12-1 x 1 x 2 6.034 - Spring 1 Single Perceptron Unit y w 0 w 1 w n w 2 w 3 x 0 =1 x 1 x 2 x 3... x
More informationStatic Gesture Recognition with Restricted Boltzmann Machines
Static Gesture Recognition with Restricted Boltzmann Machines Peter O Donovan Department of Computer Science, University of Toronto 6 Kings College Rd, M5S 3G4, Canada odonovan@dgp.toronto.edu Abstract
More informationIn Network and Distributed Systems Security Symposium (NDSS) 2018, San Diego, February Feature Squeezing:
In Network and Distributed Systems Security Symposium (NDSS) 2018, San Diego, February 2018 Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks Weilin Xu, David Evans, Yanjun Qi University
More informationIntroduction to object recognition. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others
Introduction to object recognition Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others Overview Basic recognition tasks A statistical learning approach Traditional or shallow recognition
More informationFeature Extractors. CS 188: Artificial Intelligence Fall Some (Vague) Biology. The Binary Perceptron. Binary Decision Rule.
CS 188: Artificial Intelligence Fall 2008 Lecture 24: Perceptrons II 11/24/2008 Dan Klein UC Berkeley Feature Extractors A feature extractor maps inputs to feature vectors Dear Sir. First, I must solicit
More information10-701/15-781, Fall 2006, Final
-7/-78, Fall 6, Final Dec, :pm-8:pm There are 9 questions in this exam ( pages including this cover sheet). If you need more room to work out your answer to a question, use the back of the page and clearly
More informationIntroduction to Machine Learning
Introduction to Machine Learning Maximum Margin Methods Varun Chandola Computer Science & Engineering State University of New York at Buffalo Buffalo, NY, USA chandola@buffalo.edu Chandola@UB CSE 474/574
More informationHW2 due on Thursday. Face Recognition: Dimensionality Reduction. Biometrics CSE 190 Lecture 11. Perceptron Revisited: Linear Separators
HW due on Thursday Face Recognition: Dimensionality Reduction Biometrics CSE 190 Lecture 11 CSE190, Winter 010 CSE190, Winter 010 Perceptron Revisited: Linear Separators Binary classification can be viewed
More informationHand Written Digit Recognition Using Tensorflow and Python
Hand Written Digit Recognition Using Tensorflow and Python Shekhar Shiroor Department of Computer Science College of Engineering and Computer Science California State University-Sacramento Sacramento,
More informationImperial College London. Department of Electrical and Electronic Engineering. Final Year Project Report 2018
Imperial College London Department of Electrical and Electronic Engineering Final Year Project Report 2018 Project Title: Fooling Neural Networks using Adversarial Image Perturbations Student: Guillaume
More informationAUROR: Defending Against Poisoning Attacks in Collaborative Deep Learning Systems
AUROR: Defending Against Poisoning Attacks in Collaborative Deep Learning Systems Shiqi Shen Shruti Tople Prateek Saxena National University of Singapore {shiqi04, shruti90, prateeks}@comp.nus.edu.sg ABSTRACT
More informationOn Learning and Recognition of Secure Patterns
Pa#ern Recogni-on and Applica-ons Lab On Learning and Recognition of Secure Patterns BaAsta Biggio Dept. Of Electrical and Electronic Engineering University of Cagliari, Italy University of Cagliari, Italy
More informationApplying Supervised Learning
Applying Supervised Learning When to Consider Supervised Learning A supervised learning algorithm takes a known set of input data (the training set) and known responses to the data (output), and trains
More informationSupport Vector Machines
Support Vector Machines Michael Tagare De Guzman May 19, 2012 Support Vector Machines Linear Learning Machines and The Maximal Margin Classifier In Supervised Learning, a learning machine is given a training
More informationInstance-based Learning
Instance-based Learning Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University October 15 th, 2007 2005-2007 Carlos Guestrin 1 1-Nearest Neighbor Four things make a memory based learner:
More informationLinear Discriminant Analysis in Ottoman Alphabet Character Recognition
Linear Discriminant Analysis in Ottoman Alphabet Character Recognition ZEYNEB KURT, H. IREM TURKMEN, M. ELIF KARSLIGIL Department of Computer Engineering, Yildiz Technical University, 34349 Besiktas /
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Unsupervised learning Daniel Hennes 29.01.2018 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Supervised learning Regression (linear
More informationUnderstanding Faces. Detection, Recognition, and. Transformation of Faces 12/5/17
Understanding Faces Detection, Recognition, and 12/5/17 Transformation of Faces Lucas by Chuck Close Chuck Close, self portrait Some slides from Amin Sadeghi, Lana Lazebnik, Silvio Savarese, Fei-Fei Li
More informationGENDER CLASSIFICATION USING SUPPORT VECTOR MACHINES
GENDER CLASSIFICATION USING SUPPORT VECTOR MACHINES Ashwin Swaminathan ashwins@umd.edu ENEE633: Statistical and Neural Pattern Recognition Instructor : Prof. Rama Chellappa Project 2, Part (a) 1. INTRODUCTION
More informationThe Mathematics Behind Neural Networks
The Mathematics Behind Neural Networks Pattern Recognition and Machine Learning by Christopher M. Bishop Student: Shivam Agrawal Mentor: Nathaniel Monson Courtesy of xkcd.com The Black Box Training the
More informationSupervised vs unsupervised clustering
Classification Supervised vs unsupervised clustering Cluster analysis: Classes are not known a- priori. Classification: Classes are defined a-priori Sometimes called supervised clustering Extract useful
More informationCPSC 340: Machine Learning and Data Mining. Principal Component Analysis Fall 2016
CPSC 340: Machine Learning and Data Mining Principal Component Analysis Fall 2016 A2/Midterm: Admin Grades/solutions will be posted after class. Assignment 4: Posted, due November 14. Extra office hours:
More informationarxiv: v1 [cs.cv] 16 Mar 2018
Semantic Adversarial Examples Hossein Hosseini Radha Poovendran Network Security Lab (NSL) Department of Electrical Engineering, University of Washington, Seattle, WA arxiv:1804.00499v1 [cs.cv] 16 Mar
More informationNetwork Traffic Measurements and Analysis
DEIB - Politecnico di Milano Fall, 2017 Introduction Often, we have only a set of features x = x 1, x 2,, x n, but no associated response y. Therefore we are not interested in prediction nor classification,
More informationIntroduction to Support Vector Machines
Introduction to Support Vector Machines CS 536: Machine Learning Littman (Wu, TA) Administration Slides borrowed from Martin Law (from the web). 1 Outline History of support vector machines (SVM) Two classes,
More informationSupport Vector Machines
Support Vector Machines RBF-networks Support Vector Machines Good Decision Boundary Optimization Problem Soft margin Hyperplane Non-linear Decision Boundary Kernel-Trick Approximation Accurancy Overtraining
More informationClassification: Feature Vectors
Classification: Feature Vectors Hello, Do you want free printr cartriges? Why pay more when you can get them ABSOLUTELY FREE! Just # free YOUR_NAME MISSPELLED FROM_FRIEND... : : : : 2 0 2 0 PIXEL 7,12
More informationMusic Genre Classification
Music Genre Classification Matthew Creme, Charles Burlin, Raphael Lenain Stanford University December 15, 2016 Abstract What exactly is it that makes us, humans, able to tell apart two songs of different
More informationDiscriminate Analysis
Discriminate Analysis Outline Introduction Linear Discriminant Analysis Examples 1 Introduction What is Discriminant Analysis? Statistical technique to classify objects into mutually exclusive and exhaustive
More informationAlternatives to Direct Supervision
CreativeAI: Deep Learning for Graphics Alternatives to Direct Supervision Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TUM UCL Timetable Theory and Basics State of
More information( ) =cov X Y = W PRINCIPAL COMPONENT ANALYSIS. Eigenvectors of the covariance matrix are the principal components
Review Lecture 14 ! PRINCIPAL COMPONENT ANALYSIS Eigenvectors of the covariance matrix are the principal components 1. =cov X Top K principal components are the eigenvectors with K largest eigenvalues
More informationFeature Visualization
CreativeAI: Deep Learning for Graphics Feature Visualization Niloy Mitra Iasonas Kokkinos Paul Guerrero Nils Thuerey Tobias Ritschel UCL UCL UCL TU Munich UCL Timetable Theory and Basics State of the Art
More information.. Spring 2017 CSC 566 Advanced Data Mining Alexander Dekhtyar..
.. Spring 2017 CSC 566 Advanced Data Mining Alexander Dekhtyar.. Machine Learning: Support Vector Machines: Linear Kernel Support Vector Machines Extending Perceptron Classifiers. There are two ways to
More informationFacial Expression Classification with Random Filters Feature Extraction
Facial Expression Classification with Random Filters Feature Extraction Mengye Ren Facial Monkey mren@cs.toronto.edu Zhi Hao Luo It s Me lzh@cs.toronto.edu I. ABSTRACT In our work, we attempted to tackle
More informationHandwritten English Alphabet Recognition Using Bigram Cost Chengshu (Eric) Li Fall 2015, CS229, Stanford University
Handwritten English Alphabet Recognition Using Bigram Cost Chengshu (Eric) Li chengshu@stanford.edu Fall 2015, CS229, Stanford University Abstract: This paper describes a new approach to handwritten English
More informationFace detection and recognition. Many slides adapted from K. Grauman and D. Lowe
Face detection and recognition Many slides adapted from K. Grauman and D. Lowe Face detection and recognition Detection Recognition Sally History Early face recognition systems: based on features and distances
More information