TrojanZoo is a universal pytorch platform for conducting security researches (especially for backdoor attacks/defenses) for image classification in deep leanring.
☆21Jan 7, 2021Updated 5 years ago
Alternatives and similar repositories for Trojan-Zoo
Users that are interested in Trojan-Zoo are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TrojanLM: Trojaning Language Models for Fun and Profit☆16Jun 17, 2021Updated 4 years ago
- Run fuzzing experiments in Docker☆32Mar 17, 2021Updated 5 years ago
- ☆12Jan 28, 2023Updated 3 years ago
- seed files used in UNIFUZZ experiments☆14Mar 17, 2021Updated 5 years ago
- ☆11Sep 23, 2020Updated 5 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆52Nov 1, 2020Updated 5 years ago
- Differentially private release of semantic rich data☆35Jun 17, 2021Updated 4 years ago
- A data-free backdoor detector for deep neural networks☆21Mar 8, 2023Updated 3 years ago
- The PT tracing portion of Barnum.☆11Feb 8, 2019Updated 7 years ago
- TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classifica…☆303Aug 25, 2025Updated 8 months ago
- an official PyTorch implementation of the paper "Partial Network Cloning", CVPR 2023☆13Mar 21, 2023Updated 3 years ago
- Code for generating adversarial color-shifted images☆20Nov 11, 2019Updated 6 years ago
- A large-scale dataset composed of high-quality synthetic images aimed at evaluating social biases in LVLMs☆13Apr 7, 2026Updated last month
- ☆15Apr 7, 2023Updated 3 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆11May 9, 2023Updated 3 years ago
- CVPR 2021 | Code to reproduce the results of the paper: A Khakzar, S Baselizadeh, S Khanduja, C Rupprecht, ST Kim, N Navab, Neural Respon…☆12Jun 23, 2021Updated 4 years ago
- A toolbox for backdoor attacks.☆23Jan 13, 2023Updated 3 years ago
- ☆23Oct 24, 2022Updated 3 years ago
- Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.☆381Feb 5, 2023Updated 3 years ago
- FirmSec Dataset☆12Sep 1, 2021Updated 4 years ago
- Codes for the ICLR 2022 paper: Trigger Hunting with a Topological Prior for Trojan Detection☆11Sep 19, 2023Updated 2 years ago
- ☆20Nov 27, 2022Updated 3 years ago
- ICCV 2021 papers and code focus on adversarial attacks and defense☆11Nov 5, 2021Updated 4 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- using yolov5 to detect whether people fall down or not☆11May 9, 2023Updated 3 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆33Nov 4, 2020Updated 5 years ago
- Unified Sparse Library Wrapper Based on cuSPARSE☆12May 24, 2022Updated 3 years ago
- [CCS'24] Official Implementation of "Fisher Information guided Purification against Backdoor Attacks"☆15Oct 29, 2025Updated 6 months ago
- Official implementation of Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective☆13Sep 4, 2024Updated last year
- search-based software engineering☆16Sep 17, 2014Updated 11 years ago
- Self-Distillation with weighted ground-truth targets; ResNet and Kernel Ridge Regression☆19Oct 12, 2021Updated 4 years ago
- A framework for steering MoE models by detecting and controlling behavior-linked experts.☆33Sep 12, 2025Updated 7 months ago
- Learning from Noisy Anchors for One-stage Object Detection☆27Apr 14, 2021Updated 5 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- The project page of paper: Aha! Adaptive History-driven Attack for Decision-based Black-box Models [ICCV 2021]☆10Feb 23, 2022Updated 4 years ago
- A compact toolbox for backdoor attacks and defenses.☆193Jul 16, 2024Updated last year
- ☆19Mar 24, 2023Updated 3 years ago
- Code for "Self-Distillation as Instance-Specific Label Smoothing"☆15Oct 22, 2020Updated 5 years ago
- Breaking Certifiable Defenses☆17Nov 22, 2022Updated 3 years ago
- ☆18Jun 18, 2023Updated 2 years ago
- Clone of the IDAPython repo☆23Mar 16, 2015Updated 11 years ago