Skip to main content
MyCourses MyCourses
  • Schools
    School of Arts, Design, and Architecture (ARTS) School of Business (BIZ) School of Chemical Engineering (CHEM) –sGuides for students (CHEM) – Instructions for report writing (CHEM) School of Electrical Engineering (ELEC) School of Engineering (ENG) School of Science (SCI) Language Centre Open University Library Aalto university pedagogical training program UNI (exams) Sandbox
  • CORONAVIRUS INFO
    Koronavirus - tietoa opiskelijalle Coronavirus - information for students Coronavirus - information för studerande Corona help for teachers
  • Service Links
    MyCourses - Instructions for Teachers - Teacher book your online session with a specialist - Digital tools for teaching - Personal data protection instructions for teachers - Instructions for Students - Workspace for thesis supervision Sisu Into portal for students Courses.aalto.fi Library Services - Resourcesguides - Imagoa / Open science and images IT Services Campus maps - Search spaces and see opening hours Restaurants in Otaniemi ASU Aalto Student Union Aalto Marketplace
  • ALLWELL?
    Study Skills Support for Studying Starting Point of Wellbeing About AllWell? study well-being questionnaire
  •   ‎(en)‎
      ‎(en)‎   ‎(fi)‎   ‎(sv)‎
  • Toggle Search menu
  • Hi guest! (Log in)

close

Can not find the course?
try also:

  • Sisu
  • Courses.aalto.fi

CS-E4001 - Research Seminar in Computer Science D: Research Seminar on Security and Privacy of Machine Learning, 02.03.2021-28.05.2021

This course space end date is set to 28.05.2021 Search Courses: CS-E4001

  1. Home
  2. Courses
  3. School of Science
  4. department of...
  5. cs-e4001 - re...
  6. Sections
  7. leading discu...
 
Syllabus

Leading discussion session

  • Leading discussion session

    Leading discussion session

    Guidelines

    Leading a discussion on a paper is composed of 2 parts taking 50 minutes altogether.

    1. A presentation type power point composed of the following items (20 minutes):
    1.a. An objective paper presentation that contains for instance:
    • Problem statement
    • Adversary/threat model
    • Summary of main findings & contributions
    • Results
    1.b. A critical personal synthesis that contains for instance:
    • Analysis of correctness/completeness
    • Potential flaws
    • Relation to related work
    • (A support for following discussion)
    • Etc.

    2. An interactive discussion with the rest of the class (30 minutes)
    • Prepare a set of points to discuss
    • Make it interactive and raise issues where opinions are likely to be divided
    • Develop provocative opinions
    • Ask controversial questions
    • Correlate research with recent events (e.g., news headlines on the use of AI)

    Paper assignment

    Go to this Google form and select 5 papers that you would like to present before Monday March 08, 23:55

    Presentation assignment:
    Discussion session
    Title Presenter 
    1. Model evasion
    Devil’s Whisper: A General Approach for Physical...
    Albert Mohwald
      On Adaptive Attacks to Adversarial Example Defenses
    Oliver Jarnefelt
    2. Model poisoning Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization
    Seb

    Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
    Yujia Guo
    3. Compromised training
    BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
    Paavo Reinikka
      Machine Learning Models that Remember Too Much
    Ananth Mahadevan
    4. Model stealing
    High Accuracy and High Fidelity Extraction of Neural Networks
    Albert Mohwald

    Imitation Attacks and Defenses for Black-box Machine Translation Systems
    Yujia Guo
    5. Protecting intellectual property of models
    Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
    Buse

    DAWN: Dynamic Adversarial Watermarking of Neural Networks
    Samuel
    6. Training data leakage
    The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
    Samuel
      ML-Leaks: Model and Data Independent Membership Inference Attacks...

    6. Tracing training data
    Radioactive data: tracing through training
    Oliver Jarnefelt

    Auditing Data Provenance in Text-Generation Models

    7. Privacy-preserving training
    Learning Differentially Private Recurrent Language Models


    Auditing Differentially Private Machine Learning: How Private is Private SGD?
    Paavo Reinikka
    7. Fairness & bias in ML prediction
    Characterising Bias in Compressed Models
    Ananth Mahadevan

    On the Privacy Risks of Algorithmic Fairness




    • icon for activity AssignmentPresentation 1: Slides Assignment
      Make a submission
    • icon for activity AssignmentPresentation 2: Slides Assignment
      Make a submission

Previous section

◄Materials

Next section

Paper takeaways + questions►
Skip Upcoming events
Upcoming events
Loading There are no upcoming events
Go to calendar...
  • CS-E4001 - Research Seminar in Computer Science D: Research Seminar on Security and Privacy of Machine Learning, 02.03.2021-28.05.2021
  • Sections
  • Security & Privacy of Machine Learning
  • Materials
  • Leading discussion session
  • Paper takeaways + questions
  • Programming Assignment
  • For Aalto users
  • Home
  • Calendar
  • Learner Metrics

Aalto logo

Tuki / Support
  • MyCourses help
  • mycourses(at)aalto.fi
Palvelusta
  • MyCourses rekisteriseloste
  • Tietosuojailmoitus
  • Palvelukuvaus
  • Saavutettavuusseloste
About service
  • MyCourses protection of privacy
  • Privacy notice
  • Service description
  • Accessibility summary
Service
  • MyCourses registerbeskrivining
  • Dataskyddsmeddelande
  • Beskrivining av tjänsten
  • Sammanfattning av tillgängligheten

Hi guest! (Log in)
  • Schools
    • School of Arts, Design, and Architecture (ARTS)
    • School of Business (BIZ)
    • School of Chemical Engineering (CHEM)
    • –sGuides for students (CHEM)
    • – Instructions for report writing (CHEM)
    • School of Electrical Engineering (ELEC)
    • School of Engineering (ENG)
    • School of Science (SCI)
    • Language Centre
    • Open University
    • Library
    • Aalto university pedagogical training program
    • UNI (exams)
    • Sandbox
  • CORONAVIRUS INFO
    • Koronavirus - tietoa opiskelijalle
    • Coronavirus - information for students
    • Coronavirus - information för studerande
    • Corona help for teachers
  • Service Links
    • MyCourses
    • - Instructions for Teachers
    • - Teacher book your online session with a specialist
    • - Digital tools for teaching
    • - Personal data protection instructions for teachers
    • - Instructions for Students
    • - Workspace for thesis supervision
    • Sisu
    • Into portal for students
    • Courses.aalto.fi
    • Library Services
    • - Resourcesguides
    • - Imagoa / Open science and images
    • IT Services
    • Campus maps
    • - Search spaces and see opening hours
    • Restaurants in Otaniemi
    • ASU Aalto Student Union
    • Aalto Marketplace
  • ALLWELL?
    • Study Skills
    • Support for Studying
    • Starting Point of Wellbeing
    • About AllWell? study well-being questionnaire
  •   ‎(en)‎
    •   ‎(en)‎
    •   ‎(fi)‎
    •   ‎(sv)‎