Nicholas Carlini

printf-tac-toe. tic-tac-toe in a single call to printf

yet-another-applied-llm-benchmark. A benchmark to evaluate language models on questions I've previously asked them to solve.

nn_robust_attacks. Robust evasion attacks against neural network to find adversarial examples

js13k2019-yet-another-doom-clone. Yet another doom clone (in 13kb of JavaScript)

audio_adversarial_examples. Targeted Adversarial Examples on Speech-to-Text systems

c-chat-gpt-2. C

regex-chess. A 2-ply mini-max search chess engine in 84,688 regular expressions.

nn_breaking_detection. Code corresponding to the paper "Adversarial Examples are not Easily Detected..."

pycallcc. Discount jupyter.

chess-llm. Play chess against large language models.

breaking_defensive_distillation. Python

intel-4004-in-4004-bytes-of-c. A feature-complete gate-level microcoded Intel 4004 in 4004 bytes of C, capable of emulating the original Busicom calculator ROM for which the chip was originally designed.

rhoscript. A language for code golf.

llm-biographer. Have an LLM write your biography, probably incorrectly

miniHDL. A Python Hardware Description Language DSL

AmI. Attacks Meet Interpretability

odsc_adversarial_nn. Content for ODSC west adversarial machine learning talk

breaking_efficient_defenses. Code to reproduce and break the "Efficient Defenses" paper

js13k2021-yet-another-moba. JavaScript

privacy. Library for training machine learning models with privacy for training data

pixel-deflection. Deflecting Adversarial Attacks with Pixel Deflection

cleverhans. A library for benchmarking vulnerability to adversarial examples

js13k2020-yet-another-space-shooter. JavaScript

Open-Prompt-Injection. This repository provides a benchmark for prompt Injection attacks and defenses

equational_theories. A project to map out the relations between different equational theories of Magmas.

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

foolbox. Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, Keras, …

MagNet. MagNet: a Two-Pronged Defense against Adversarial Examples

adv-eval-paper. LaTeX source for the paper "On Evaluating Adversarial Robustness"

t-bench. JetBrains MPS

APE-GAN. Tensorflow implementation of Our APE-GAN

arduino-apple-profile-reader. A short script to read data off of an Apple ProFile hard drive with an Arduino.

nmt. TensorFlow Neural Machine Translation Tutorial

Adv360-Pro-ZMK. Production repository for the all-new Advantage360 Professional using ZMK engine

open_clip. An open source implementation of CLIP.

ImageNet-Adversarial-Training. Feature Denoising for Improving Adversarial Robustness

arxiv-sanity-preserver. Web interface for browsing, search and filtering recent arxiv submissions