carlini

obfuscated-gradients

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

audio_adversarial_examples

Targeted Adversarial Examples on Speech-to-Text systems

c-chat-gpt-2

js13k2019-yet-another-doom-clone

Yet another doom clone (in 13kb of JavaScript)

nn_breaking_detection

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

nn_robust_attacks

Robust evasion attacks against neural network to find adversarial examples

printf-tac-toe

tic-tac-toe in a single call to printf

pycallcc

Discount jupyter.

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

deduplicate-text-datasets

carlini/breaking_defensive_distillation

carlini/rhoscript

A language for code golf.

carlini/arxiv-sanity-preserver

Web interface for browsing, search and filtering recent arxiv submissions