A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Contexts Optical Compression

Universal and Transferable Attacks on Aligned Language Models

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Source code of IPA, https://escholarship.org/uc/item/2p0805dq

A low-latency prediction-serving system

gSlice Slicing GPUs to Serve Heterogeneous Inference Requests

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, …

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning mode…

Fast Multimodal LLM on Mobile Devices

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

🛡 A curated list of adversarial attacks in PyTorch, with a focus on transferable black-box attacks.

PyTorch implementation of adversarial attacks [torchattacks]

CanarySEFI is a framework for evaluating the robustness of deep learning-based image recognition models. It can evaluate model robustness and attack/defense algorithm effectiveness, encompassing 26…

电子科技大学2022级研究生课程《图论及其应用》，包含教材、课件、作业和复习时写的东西。

🎓电子科技大学 📔课程资料

Experimental code for the paper "Practical Over-Threshold Multi-Party Private Set Intersection"

c++实现的Paillier算法库

Private set intersection using garbled bloom filters in semi-honest setting

Multi-party Private Set Intersections & Threshold Set Intersections

Curated collection of papers in MoE model inference