carlini

I break things

Pinned Repositories

obfuscated-gradients
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
Language:Jupyter Notebook884 48 0171
audio_adversarial_examples
Targeted Adversarial Examples on Speech-to-Text systems
Language:Python292 13 4191
c-chat-gpt-2
Language:C170 2 018
js13k2019-yet-another-doom-clone
Yet another doom clone (in 13kb of JavaScript)
Language:JavaScript292 12 567
nn_breaking_detection
Code corresponding to the paper "Adversarial Examples are not Easily Detected..."
Language:Python84 9 026
nn_robust_attacks
Robust evasion attacks against neural network to find adversarial examples
Language:Python805 23 42231
printf-tac-toe
tic-tac-toe in a single call to printf
Language:C2.2k 29 953
pycallcc
Discount jupyter.
Language:Python43 2 00
yet-another-applied-llm-benchmark
A benchmark to evaluate language models on questions I've previously asked them to solve.
Language:Python936 17 1467
deduplicate-text-datasets
Language:Rust1.1k 13 41112

carlini's Repositories

carlini/printf-tac-toe
tic-tac-toe in a single call to printf
Language:C2.2k 29 953
carlini/yet-another-applied-llm-benchmark
A benchmark to evaluate language models on questions I've previously asked them to solve.
Language:Python936 17 1467
carlini/nn_robust_attacks
Robust evasion attacks against neural network to find adversarial examples
Language:Python805 23 42231
carlini/audio_adversarial_examples
Targeted Adversarial Examples on Speech-to-Text systems
Language:Python292 13 4191
carlini/js13k2019-yet-another-doom-clone
Yet another doom clone (in 13kb of JavaScript)
Language:JavaScript292 12 567
carlini/c-chat-gpt-2
Language:C170 2 018
carlini/nn_breaking_detection
Code corresponding to the paper "Adversarial Examples are not Easily Detected..."
Language:Python84 9 026
carlini/pycallcc
Discount jupyter.
Language:Python43 2 00
carlini/chess-llm
Play chess against large language models.
Language:Python40 3 06
carlini/AmI
Attacks Meet Interpretability
Language:Jupyter Notebook9 5 01
carlini/breaking_efficient_defenses
Code to reproduce and break the "Efficient Defenses" paper
Language:Python8 3 01
carlini/privacy
Library for training machine learning models with privacy for training data
Language:Python6 4 03
carlini/cleverhans
A library for benchmarking vulnerability to adversarial examples
Language:Python5 5 05
carlini/pixel-deflection
Deflecting Adversarial Attacks with Pixel Deflection
Language:Jupyter Notebook5 4 02
carlini/img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
Language:Python4 1 0
carlini/js13k2021-yet-another-moba
Language:JavaScript4 3 02
carlini/js13k2020-yet-another-space-shooter
Language:JavaScript3 3 01
carlini/adv-eval-paper
LaTeX source for the paper "On Evaluating Adversarial Robustness"
Language:TeX2 5 0
carlini/APE-GAN
Tensorflow implementation of Our APE-GAN
Language:Python2 4 0
carlini/equational_theories
A project to map out the relations between different equational theories of Magmas.
Language:C2
carlini/foolbox
Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras, …
Language:Python2 4 0
carlini/MagNet
MagNet: a Two-Pronged Defense against Adversarial Examples
Language:Python2 3 03
carlini/Adv360-Pro-ZMK
Production repository for the all-new Advantage360 Professional using ZMK engine
Language:Shell1 1 0
carlini/arduino-apple-profile-reader
A short script to read data off of an Apple ProFile hard drive with an Arduino.
Language:C1 2 0
carlini/nmt
TensorFlow Neural Machine Translation Tutorial
Language:Python1 4 0
carlini/objax
Language:Python1 3 0
carlini/open_clip
An open source implementation of CLIP.
Language:Python1 2 0
carlini/backpropagation-clipping
Language:Python1 0
carlini/gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
Language:Python2 0
carlini/ImageNet-Adversarial-Training
Feature Denoising for Improving Adversarial Robustness
Language:Python4 0