Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Attacks on Machine Learning
Search
prabhant
October 27, 2017
Programming
0
460
Attacks on Machine Learning
Presentation for my talk on attacks on machine learning at PyconUK 2017
prabhant
October 27, 2017
Tweet
Share
More Decks by prabhant
See All by prabhant
Masters Thesis
prabhant
0
33
Class Imbalance Problem
prabhant
0
110
Gotchas of Pandas
prabhant
0
110
Other Decks in Programming
See All in Programming
DocC Tutorial と TCA におけるテスト機能の紹介
kalupas226
1
330
とにかくHTTP3をライトニングに話す / Anyway, I'll talk to Lightning about HTTP3.
seike460
PRO
0
120
incrementalモデルの理解を深める
ikkimiyazaki
2
640
孤独のCTOグルメという やや奇抜な企画をやった目的と効果
shoheimitani
3
1k
プロンプトエンジニアリング入門
tomokusaba
2
990
Why 1 + 1 = 2 in Swift?
1plus4
1
250
上手な探索的テストとその上達方法について
matsu802
4
660
Compiling Python to WebAssembly with py2wasm
syrusakbary
0
140
ファイル先頭の use の意味、説明できますか? 〜PHP の namespace と autoloading の関係を正しく理解しよう〜 / namespace and autoloading in php
okashoi
2
470
イベントストーミングによるオブジェクトモデリング・オブジェクト指向プログラミングの適用・開発プロセスの変遷・アーキテクチャの変革 / Object modeling with Event Storming.
nrslib
12
3.3k
設計の知識と技能で駆動するソフトウェア開発
masuda220
PRO
19
11k
Laravel標準バリデーションでできること
hmb_ok
2
360
Featured
See All Featured
The Language of Interfaces
destraynor
150
23k
Code Review Best Practice
trishagee
54
15k
Art, The Web, and Tiny UX
lynnandtonic
288
19k
GitHub's CSS Performance
jonrohan
1023
450k
How To Stay Up To Date on Web Technology
chriscoyier
781
250k
It's Worth the Effort
3n
180
27k
The Power of CSS Pseudo Elements
geoffreycrofte
58
4.9k
StorybookのUI Testing Handbookを読んだ
zakiyama
10
4.5k
Into the Great Unknown - MozCon
thekraken
10
830
No one is an island. Learnings from fostering a developers community.
thoeni
14
2k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
355
22k
Learning to Love Humans: Emotional Interface Design
aarron
266
39k
Transcript
None
About me • Security + Data science • Master’s student
at University of Tartu, Estonia
• What’s adversarial ML
• What’s adversarial ML • Goals of adversarial examples
• What’s adversarial ML • Goals of adversarial examples •
Algorithms to craft adversarial examples
• What’s adversarial ML • Goals of adversarial examples •
Algorithms to craft adversarial examples • Defense against adversarial examples(BONUS)
What’s Machine learning?
What’s Adversarial ML
What’s Adversarial ML =Security + ML
History Lesson!!
Where it started: • PRALab Unica
Where it started: • PRALab Unica Now: • Everyone First
paper: https://arxiv.org/pdf/1312.6199.pdf
Source: https://pralab.diee.unica.it/en/wild-patterns
Types of attacks • Whitebox • Blackbox
Ways to Attacks
Ways to Attacks Poisoning training data (train time attack)
Ways to Attacks Poisoning training data (Train time attack) Crafting
adversarial examples (Test time attack)
Adversarial examples goals • Confidence reduction: reduce the output confidence
classification
Adversarial examples goals • Confidence reduction • Misclassification: Changing the
output class
Adversarial examples goals • Confidence reduction • Misclassification • Targeted
misclassification: produce inputs that produce the output of a specific class
Adversarial examples goals • Confidence reduction • Misclassification • Targeted
misclassification • Source target misclassification: specific input gives specific output
How does Attacking ML models work?
How adversarial Examples work Source: cleverhans.io
Deep Neural Networks are Easily Fooled: High Confidence Predictions for
Unrecognizable Images :https://arxiv.org/pdf/1412.1897.pdf
Source: Adversarial Examples for Evaluating Reading Comprehension Systems Source: https://arxiv.org/pdf/1707.07328.pdf
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method 2. JSMA: jacobian based saliency map attack
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method 2. JSMA: jacobian based saliency map attack 3. Carlini wagner attack
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method 2. JSMA: jacobian based saliency map attack 3. Carlini wagner attack 4. DeepFool
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method 2. JSMA: jacobian based saliency map attack 3. Carlini wagner attack 4. DeepFool 5. The Basic Iterative Method
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method 2. JSMA: jacobian based saliency map attack 3. Carlini wagner attack 4. DeepFool 5. The Basic Iterative Method 6. EAD: Elastic-Net Attacks
Algorithms to craft adversarial examples for NN 1. FGSM: fast
gradient sign method 2. JSMA: jacobian based saliency map attack 3. Carlini wagner attack 4. DeepFool 5. The Basic Iterative Method 6. EAD: Elastic-Net Attacks 7. Projected Gradient Descent Attack PS: these are only the famous one’s
BlackBox : How can it even be possible :( ?
Transferability The Space of Transferable Adversarial Examples: https://arxiv.org/pdf/1704.03453.pdf
Why should I Care?
Why should I Care?
Why should I Care?
Why should I Care?
None
But they aren’t that easy to make.. Are they :(
None
Then How to defend the Models against adversarial examples •
Adversarial Training ◦ Ensemble adversarial training • Defensive distillation
None
Libraries and resources • Cleverhans(Tensorflow) • FoolBox(bethgelab) • Secure ML
Library(not released) • Tools from PRA Lab • My blog
Thank You Q/A time <Don’t ask “WHY” because nobody knows>
Twitter: @prabhantsingh Linkedin: https://www.linkedin.com/in/prabhantsingh Github: @prabhant