Raytsang123

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

TextFooler

A Model for Natural Language Attack on Text Classification and Inference

adv-patch-paper-list

A paper list for localized adversarial patch research

adversarial-robustness-toolbox

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

AI-Security-and-Privacy-Events

A curated list of workshops and tutorials on AI Security & Privacy

awesome-ai-agents

A list of AI autonomous agents

Awesome-Dataset-Distillation

Awesome Dataset Distillation Papers

Awesome-Diffusion-Models

A collection of resources and papers on Diffusion Models and Score-based Models, a darkhorse in the field of Generative Models

awesome-phd-advice

Collection of advice for prospective and current PhD students

Black-Box-Tuning

Source code for paper "Black-Box Tuning for Language-Model-as-a-Service"

DART

Code for the ICLR2022 paper "Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners"

DeepHash-pytorch

Implementation of Some Deep Hash Algorithms, Including DPSH、DSH、DHN、HashNet、DSDH、DTSH、DFH、GreedyHash、CSQ.

DL-based-Android-Malware-Defenses-review

Papers, code and datasets about deep learning for Android malware defenses and malware detection

graph-adversarial-learning-literature

A curated list of adversarial attacks and defenses papers on graph-structured data.

LMaaS-Papers

Awesome papers on Language-Model-as-a-Service (LMaaS)

machine_unlearning

Existing Literature about Machine Unlearning

MOTH

This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Security."

neural-tangents

Fast and Easy Infinite Neural Networks in Python

NLP_Backdoor

Hidden backdoor attack on NLP systems

PICCOLO

PLMPapers-1

A paper list of pre-trained language models (PLMs).

PromptPapers

Must-read papers on prompt-based tuning for pre-trained language models.

propaganda_as_a_service

Code for paper: "Spinning Language Models for Propaganda-As-A-Service"

RAP

Code for the paper "RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models" (EMNLP 2021)

Robust-Prefix-Tuning

code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification

Robustness-Against-Backdoor-Attacks

RAB: Provable Robustness Against Backdoor Attacks

semantic-randomized-smoothing

Semantic Randomized Smoothing

SuperGen

Generating Training Data with Language Models: Towards Zero-Shot Language Understanding

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

trojanzoo

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.