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
560
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
46
Class Imbalance Problem
prabhant
0
180
Gotchas of Pandas
prabhant
0
120
Other Decks in Programming
See All in Programming
「リーダーは意思決定する人」って本当?~ 学びを現場で活かす、リーダー4ヶ月目の試行錯誤 ~
marina1017
0
170
#QiitaBash TDDで(自分の)開発がどう変わったか
ryosukedtomita
1
360
AI Ramen Fight
yusukebe
0
130
Claude Code で Astro blog を Pages から Workers へ移行してみた
codehex
0
180
iOS開発スターターキットの作り方
akidon0000
0
240
DataformでPythonする / dataform-de-python
snhryt
0
160
Flutter로 Gemini와 MCP를 활용한 Agentic App 만들기 - 박제창 2025 I/O Extended Seoul
itsmedreamwalker
0
130
Strands Agents で実現する名刺解析アーキテクチャ
omiya0555
1
120
中級グラフィックス入門~効率的なメッシュレット描画~
projectasura
4
2.5k
CLI ツールを Go ライブラリ として再実装する理由 / Why reimplement a CLI tool as a Go library
ktr_0731
3
1k
新世界の理解
koriym
0
130
Google I/O Extended Incheon 2025 ~ What's new in Android development tools
pluu
1
250
Featured
See All Featured
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
26k
Code Reviewing Like a Champion
maltzj
524
40k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.8k
Balancing Empowerment & Direction
lara
1
540
A designer walks into a library…
pauljervisheath
207
24k
Into the Great Unknown - MozCon
thekraken
40
2k
Why You Should Never Use an ORM
jnunemaker
PRO
58
9.5k
Agile that works and the tools we love
rasmusluckow
329
21k
A better future with KSS
kneath
239
17k
Making Projects Easy
brettharned
117
6.3k
How STYLIGHT went responsive
nonsquared
100
5.7k
Measuring & Analyzing Core Web Vitals
bluesmoon
8
550
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