Analyzing Federated Learning through an Adversarial Lens Arjun Nitin - PowerPoint PPT Presentation

Aug 28, 2022 •858 likes •1.46k views

Analyzing Federated Learning through an Adversarial Lens Arjun Nitin Bhagoji 1 , Supriyo Chakraborty 2 , Prateek Mittal 1 and Seraphin Calo 2 1 Princeton University 2 IBM Research ICML 2019 Federated learning (with a malicious agent) Federated

Analyzing Federated Learning through an Adversarial Lens Arjun Nitin Bhagoji 1 , Supriyo Chakraborty 2 , Prateek Mittal 1 and Seraphin Calo 2 1 Princeton University 2 IBM Research ICML 2019
Federated learning (with a malicious agent)
Federated learning (with a malicious agent) McMahan et al., Communication- Efficient Learning of Deep Networks from Decentralized Data , AISTATS 2017
Federated learning (with a malicious agent) Global Server McMahan et al., Communication- Efficient Learning of Deep Networks from Decentralized Data , AISTATS 2017

Recommend

Federated Learning Min Du Postdoc, UC Berkeley Outline q Preliminary: deep learning and SGD q

Federated Learning Min Du Postdoc, UC Berkeley Outline q Preliminary: deep learning and SGD q Federated learning: FedSGD and FedAvg q Related research in federated learning q Open problems Outline q Preliminary: deep learning and SGD q Federated

620 views • 50 slides

Differentially-Private Federated Linear Bandits Introduction Federated Learning Contextual

Differentially- Private Federated Linear Bandits Dubey and Pentland June 2020 Differentially-Private Federated Linear Bandits Introduction Federated Learning Contextual Bandits Summary Background Abhimanyu Dubey and Alex Pentland

439 views • 20 slides

MK Lens Promotion New Lens Concept Keep 4K Cabrio quality, Light weight, Compact, Affordable,

MK Lens Promotion New Lens Concept Keep 4K Cabrio quality, Light weight, Compact, Affordable, Cinema zoom lens!! MK18-55mm T2.9 MK50-135mm T2.9 Model Name Lens Mount Sony E mount Sony E mount Focal Langth 18-55mm 50-135mm Zoom Ration

551 views • 9 slides

Fair Resource Allocation in Federated Learning Tian Li (CMU) , Maziar Sanjabi (Facebook AI), Ahmad

Fair Resource Allocation in Federated Learning Tian Li (CMU) , Maziar Sanjabi (Facebook AI), Ahmad Beirami (Facebook AI), Virginia Smith (CMU) tianli@cmu.edu 1 Federated Learning 2 2 Federated Learning Privacy-preserving training in

1.19k views • 55 slides

Federated Machine Learning via Over-the-Air Computation Yuanming Shi ShanghaiTech University 1

Federated Machine Learning via Over-the-Air Computation Yuanming Shi ShanghaiTech University 1 Outline Motivations Big data, IoT,AI Three vignettes: Federated machine learning Federated model aggregation Over-the-air

1.03k views • 56 slides

1 Converging Lenses Biconvex lens Planoconvex lens Positive meniscus lens Oct 289:56 AM

Lenses 2 types converging and diverging Oct 289:52 AM Converging Lenses rays that are parallel to the principal axis, strike the lens, and converge to a single point on the opposite side of the lens (they pass through 2 surfaces) Oct

705 views • 10 slides

CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial

CSC321 Lecture 22: Adversarial Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Adversarial Learning 1 / 26 Overview Two topics for today: Adversarial examples: examples carefully crafted to cause an undesirable behavior (e.g.

416 views • 26 slides

Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs

Deep Adversarial Learning for NLP 9:00 10:30 Introduction and Adversarial Training, GANs William Wang 10:30 11:00 Break - 11:00 12:15 Adversarial Examples Sameer Singh 12:15 12:30 Conclusions and Question Answering William

1.76k views • 105 slides

CONDENSER CONDENSER LENS LENS AMRITA CHAKRABORTY 02/01/2016 WHAT IS IT? CONDENSER is a

INSTRUMENTAL TECHNIQUE PRESENTATION CONDENSER CONDENSER LENS LENS AMRITA CHAKRABORTY 02/01/2016 WHAT IS IT? CONDENSER is a lens that serves to concentrate light from the illumination source in a microscope that is in turn focused

238 views • 10 slides

E-lens APEX Study Plan E-lens teams HOBBC experiments at 255 GeV Test of lattice

E-lens APEX Study Plan E-lens teams HOBBC experiments at 255 GeV Test of lattice Dynamic Aperture (in operations with 1 BB collision) Polarization and polarization lifetime (in operation) Phase advance IP8 to e-lens (setup or

218 views • 8 slides

Question: If youre building a camera and want to make a larger image (a telephoto lens) you

Question: If youre building a camera and want to make a larger image (a telephoto lens) you should: Cameras 1. increase the diameter of the lens 2. decrease the diameter of the lens 3. increase the curvature of the lens 4. decrease the

312 views • 3 slides

Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning

Adversarial Learning Bounds for Linear Classes and Neural Nets Understanding Adversarial Learning through Rademacher Complexity Pranjal Awasthi, Natalie Frank, Mehryar Mohri Google Research & Courant Institute August 14, 2020 1 / 17

401 views • 17 slides

Docker in the EGI Docker in the EGI Federated Cloud Federated Cloud Carlos Gimeno

Docker in the EGI Docker in the EGI Federated Cloud Federated Cloud Carlos Gimeno cgimeno@bifi.es Instituto de Biocomputacin y Fsica de Sistemas Complejos info@bifi.es http://bifi.es 0. Index Introduction What is Docker? A

401 views • 14 slides

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY

SECURITY, ADVERSARIAL SECURITY, ADVERSARIAL LEARNING, AND PRIVACY LEARNING, AND PRIVACY Christian Kaestner with slides from Eunsuk Kang Required reading: Hulten, Geoff. "Building Intelligent Systems: A Guide to Machine Learning

1.95k views • 113 slides

Stronger and Faster Wasserstein Adversarial Attacks Kaiwen Wu kaiwen.wu@uwaterloo.ca Joint work

Stronger and Faster Wasserstein Adversarial Attacks Kaiwen Wu kaiwen.wu@uwaterloo.ca Joint work with Allen Wang and Yaoliang Yu K.Wu, A.Wang and Y.Yu Wasserstein Adversarial Attacks July 29, 2020 1 / 18 Adversarial Examples Adversarial

1.04k views • 38 slides

Confidence-Calibrated Adversarial Training Generalizing to Unseen Attacks David Stutz, Matthias

Confidence-Calibrated Adversarial Training Generalizing to Unseen Attacks David Stutz, Matthias Hein, Bernt Schiele 2-Minute Overview Problem: Robustness to various adversarial examples. Adversarial training on L adversarial examples:

636 views • 34 slides

You Wont Believe It: Exploring the Advertising Ecosystem of Fake News Websites Catherine Han

You Wont Believe It: Exploring the Advertising Ecosystem of Fake News Websites Catherine Han Allen Tong CS 261N 1 Misinformation Flavors: Deception 2 Misinformation Flavors: Junk Science 3 Misinformation Flavors: Unreliable Clickbait 4

556 views • 24 slides

Bridging Missing Gaps in Evaluating DDoS Research Lumin Shi, Samuel Mergendahl, Devkishen

Bridging Missing Gaps in Evaluating DDoS Research Lumin Shi, Samuel Mergendahl, Devkishen Sisodia, Jun Li {luminshi, smergend, dsisodia, lijun}@cs.uoregon.edu University of Oregon Preliminary Work Paper (Short Paper) DDoS Attacks Today

224 views • 19 slides

Joint Liver Lesion Segmentation and Classification via Transfer Learning Michal Heker and Hayit

Joint Liver Lesion Segmentation and Classification via Transfer Learning Michal Heker and Hayit Greenspan Department of Biomedical Engineering, Tel-Aviv University, Israel July 2020 Contact : michalheker@gmail.com Medical Image Processing Lab

103 views • 6 slides

Evaluating the Long-term Effects of Parameters on the Characteristics of the Tranco Top Sites

Evaluating the Long-term Effects of Parameters on the Characteristics of the Tranco Top Sites Ranking Victor Le Pochat , Tom Van Goethem, Wouter Joosen CSET 2019, 12 August 2019 Security researchers rely on top websites rankings We perform a

705 views • 27 slides

Green Chemistry Student Resources Examples of What You Can Do! Lead or Join a Student led

beyondbenign green chemistry education Green Chemistry Student Resources Examples of What You Can Do! Lead or Join a Student led initiative ACS-GCI- encourage your Chemistry Club to get a green chemistry award Encourage your Chemistry

256 views • 7 slides

# of true positives true positive rate = # of known positives (Proportion of actual positives

True positive rate (Sensitivity) # of true positives true positive rate = # of known positives (Proportion of actual positives that are correctly identified) True negative rate (Specificity) # of true negatives true negative rate = # of known

476 views • 24 slides

Attacking the stack Thanks to SysSec and Secure Systems Labs at Vienna University of Technology

Attacking the stack Thanks to SysSec and Secure Systems Labs at Vienna University of Technology for some of these slides Attacking the stack We have seen how the stack works. Now: lets see how we can abuse this. We have already seen how code

674 views • 47 slides

AccessMiner: Using System-Centric Models for Malware Protection Andrea Lanzi 1 Davide Balzarotti 1

AccessMiner: Using System-Centric Models for Malware Protection Andrea Lanzi 1 Davide Balzarotti 1 Christopher Kruegel 2 Mihai Christodorescu 3 Engin Kirda 1 1 Institute Eurecom 2 UC Santa Barbara 3 IBM T.J. Watson Research 17th ACM Conference on

546 views • 43 slides

Download document

More recommend

Explore More Topics

Stay informed with curated content and fresh updates.

animals pets art culture automotive transportation business finance computer internet construction architecture education-career electronics communication