test- bzw. researchpages...:

Maschinelles Sprechen	Per noMachine auf AI-Lab-Rechner zugreifen	Maschinelles Lernen	Maschinelles Lesen	Maschinelles Dichten
KHM-Wolke einrichten	"...Sprache"	Vergleichsoperatoren	Perzeptron	Boole
Code Poetry	tesssts	AI@exLabIII	Einführung in die Programmierung Künstlicher Intelligenzen	Future Minds – Kritik Künstlicher Intelligenzen
Kommandozeilenreferenz	jutta-weber-kommentar	Die Kommandozeile	praktische Erinnerungskultur	Krieg & KI
das Codicht	machtkaputtwaseuchkaputtmachtstuktur	PAD-exp-inf.-talk@aula	PAD-ki_research	PAD-booklist
PAD-wo-beginnt-der-krieg_abstract	notes_rechnen mit lebenden systeme	seminar-notes	AI on Rasp Pi	krieg-u-ki-test
Per Teamviewer auf AI-Lab-Rechner zugreifen	Kriegseinführung	Krieg-u-Ki-Archivseite	notes-poiesis_SS18	Poiesis and Pottery
RunwayML	ChatterBot	python-intro-brainstorming	TextBlob	sentiment analysis

KI-Newsletter 4

--- how to get your trainigdata

esolangs:

Beatnik

Hacks

jupyter: jupyter-extensions

KHM-Cloud

AI Dungeon

digitale poesie:

https://0x0a.li/de/ https://poesiefestival.org/de/mediathek/digitale-poesie/

dann die arbeiten von thurston, bajohr, morris, goldsmith etc...

https://de.wikipedia.org/wiki/Digitale_Poesie

Inhaltsverzeichnis

1 Keras Examples
2 ADVERSARIAL ATTACKS
3 WHITE BOX ATTACKS
4 BLACK BOX ATTACKS
5 ETHICS
6 XAI
- 6.1 XAI durch Sprachrationalisierung
7 LANGUAGE
8 REPRODUKTIVE KI

Keras Examples

https://github.com/keras-team/keras/tree/master/examples

einfaches perceptron (schöne skizzen): https://github.com/nature-of-code/NOC-S17-2-Intelligence-Learning/blob/master/week4-neural-networks/perceptron.pdf

ADVERSARIAL ATTACKS

KNN's sind extrem anfällig für...

https://singularityhub.com/2017/10/10/ai-is-easy-to-fool-why-that-needs-to-change

https://en.wikipedia.org/wiki/Deep_learning#Cyberthreat

WHITE BOX ATTACKS

https://cv-tricks.com/how-to/breaking-deep-learning-with-adversarial-examples-using-tensorflow/
- Paper »ADVERSARIAL EXAMPLES IN THE PHYSICAL WORLD«: https://arxiv.org/pdf/1607.02533.pdf

Untargeted Adversarial Attacks

Adversarial attacks that just want your model to be confused and predict a wrong class are called Untargeted Adversarial Attacks.

nicht zielgerichtet

Fast Gradient Sign Method(FGSM)

FGSM is a single step attack, ie.. the perturbation is added in a single step instead of adding it over a loop (Iterative attack).

Basic Iterative Method

Störung, anstatt in einem einzelnen Schritt in mehrere kleinen Schrittgrößen anwenden

Iterative Least-Likely Class Method

ein Bild erstellen, welches in der Vorhersage den niedrigsten Score trägt

Targeted Adversarial Attacks

Attacks which compel the model to predict a (wrong) desired output are called Targeted Adversarial attacks

zielgerichtet

(Un-)Targeted Adversarial Attacks

kann beides...

Projected Gradient Descent (PGD)

Eine Störung finden die den Verlust eines Modells bei einer bestimmten Eingabe maximiert:

MNIST-Bsp.: https://towardsdatascience.com/know-your-enemy-7f7c5038bdf3
- Jupyter Notebook: https://github.com/oscarknagg/adversarial/blob/master/notebooks/Creating_And_Defending_From_Adversarial_Examples.ipynb

BLACK BOX ATTACKS

https://medium.com/@ml.at.berkeley/tricking-neural-networks-create-your-own-adversarial-examples-a61eb7620fd8
- Jupyter Notebook: https://github.com/dangeng/Simple_Adversarial_Examples

on computer vision

propose zeroth order optimization (ZOO)

attacks to directly estimate the gradients of the targeted DNN
- https://arxiv.org/abs/1708.03999

Black-Box Attacks using Adversarial Samples

a technique that uses the victim model as an oracle to label a synthetic training set for the substitute, so the attacker need not even collect a training set to mount the attack
- https://arxiv.org/abs/1605.07277