Chawin Sitawarin

llm-sp. Papers and resources related to the security and privacy of LLMs 🤖

Adversarial-Examples-Reading-List. This is the reading list mainly on adversarial examples (attacks, defenses, etc.) I try to keep and update regularly.

pal. PAL: Proxy-Guided Black-Box Attack on Large Language Models

adv-part-model. Code for a research paper "Part-Based Models Improve Adversarial Robustness" (ICLR 2023)

knn-defense. Adversarial Examples on KNN (and its neural network friends)

bagnet-adv. Exploring how BagNet can be used for interpretability and defending adversarial examples

adv-patch-bench. Jupyter Notebook

Adversarial-Examples-GAN. Jupyter Notebook

DART. Code for the 'DARTS: Deceiving Autonomous Cars with Toxic Signs' paper

dknn_attack. Demonstrate attacks on kNN and Deep kNN

ates-minimal. Improving Adversarial Robustness Through Progressive Hardening (AutoAttack test)

DataAugGAN. COS 429 Final Project: Data Augmentation with GAN (Fall 17)

adv-exp. Experiments on adversarial examples