SCLBD

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

VideoCrafter

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

sam

SAM: Sharpness-Aware Minimization (PyTorch)

Awesome-Segment-Anything

This repository is for the first comprehensive survey on Meta AI's Segment Anything Model (SAM).

LaVIN

[NeurIPS 2023] Official implementations of "Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models"

DeepfakeBench

A comprehensive benchmark of deepfake detection

GeoDataViz-Toolkit

The GeoDataViz Toolkit is a set of resources that will help you communicate your data effectively through the design of compelling visuals. In this repository we are sharing resources, assets and other useful links.

BackdoorBench

cords

Reduce end to end training time from days to hours (or hours to minutes), and energy requirements/costs by an order of magnitude using coresets and data selection.

LAMM

[NeurIPS 2023 Datasets and Benchmarks Track] LAMM: Multi-Modal Large Language Models and Applications as AI Agents

Awesome-Backdoor-in-Deep-Learning

A curated list of papers & resources on backdoor attacks and defenses in deep learning.

BlackboxBench

I-BAU

Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''

Transfer_attack_RAP

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)

DBD

CNN-FCF-CVPR-2019

CGATTACK

Official repository for CVPR 2022 paper 'Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution'

lgv-geometric-transferability

Source of the ECCV22 paper "LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity"

Versatile-Weight-Attack

The implementatin of Versatile Weight Attack via Flipping Limited Bits, including Singel Sample Attack and Triggered Samples Attack.

iccv2021_meta_attack

ISSBA

Invisible Backdoor Attack with Sample-Specific Triggers

Parallel-Rectangle-Flip-Attack-A-Query-based-Black-box-Attack-against-Object-Detection

A Implementation of ICCV-2021(Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection)

ProS-GAN

PUM

[CVPR 2021] Pytorch implementation for Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation

TA-LBF

The implementatin of our ICLR 2021 work: Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

TediGAN

[CVPR 2021] Pytorch implementation for TediGAN: Text-Guided Diverse Face Image Generation and Manipulation.