This is your work, valued

Chawin Sitawarin

Expert
@chawins

MTS @ Anthropic (prev. Google DeepMind, Meta, and UC Berkeley). ML security & privacy.

chawins.github.io

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

579

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

229

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

57

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

21

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

20

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

4

adv-patch-bench. Jupyter Notebook

3

Adversarial-Examples-GAN. Jupyter Notebook

2

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

2

dknn_attack. Demonstrate attacks on kNN and Deep kNN

2

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

2

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

1

adv-exp. Experiments on adversarial examples

1