This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models".
☆24Jul 3, 2024Updated 2 years ago
Alternatives and similar repositories for BEEAR
Users that are interested in BEEAR are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Aug 15, 2022Updated 4 years ago
- ☆25Jul 25, 2024Updated 2 years ago
- The code implementation of GraCeFul (Accepted in COLING 2025)☆14Jan 27, 2025Updated last year
- Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders☆39Sep 25, 2023Updated 3 years ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆20Jun 7, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- The implementation for paper "UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in …☆17Jul 3, 2025Updated last year
- Code for paper "Universal Jailbreak Backdoors from Poisoned Human Feedback"☆68Apr 24, 2024Updated 2 years ago
- Data-free knowledge distillation using Gaussian noise (NeurIPS paper)☆15Mar 24, 2023Updated 3 years ago
- ☆51Sep 29, 2024Updated 2 years ago
- ☆25May 6, 2021Updated 5 years ago
- [ICCV'2025 Highlight] Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation☆10Mar 30, 2026Updated 7 months ago
- Example TrojAI Submission☆27Aug 25, 2026Updated 2 months ago
- ☆28Aug 21, 2023Updated 3 years ago
- Benchmark evaluation code for "SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal" (ICLR 2025)☆86Mar 1, 2025Updated last year
- 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.
- ☆26Dec 1, 2022Updated 3 years ago
- 🔥🔥🔥 Detecting hidden backdoors in Large Language Models with only black-box access☆61Jun 2, 2025Updated last year
- DO NOT RUN THIS.☆10Jul 31, 2026Updated 3 months ago
- Composite Backdoor Attacks Against Large Language Models☆26Apr 12, 2024Updated 2 years ago
- Official code for "Algorithmic Capabilities of Random Transformers" (NeurIPS 2024)☆16Sep 28, 2024Updated 2 years ago
- A repository for pretraining a discrete diffusion model (llada), with all components built on the Hugging Face ecosystem.☆13Aug 27, 2025Updated last year
- The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recogn…☆125May 9, 2023Updated 3 years ago
- [Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks☆13Feb 26, 2023Updated 3 years ago
- ☆39Oct 17, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆29Aug 8, 2025Updated last year
- Reference implementation for DPO (Direct Preference Optimization)☆13Jan 18, 2024Updated 2 years ago
- [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training☆38Apr 7, 2025Updated last year
- Benchmarking MIAs against LLMs.☆30Oct 8, 2024Updated 2 years ago
- [NeurIPS 2024] "Membership Inference on Text-to-image Diffusion Models via Conditional Likelihood Discrepancy"☆12Sep 15, 2025Updated last year
- Influence Maximization Paper List☆11May 11, 2022Updated 4 years ago
- ☆10Mar 13, 2024Updated 2 years ago
- ☆26Aug 21, 2024Updated 2 years ago
- bert蒸馏实践,包含BiLSTM蒸馏BERT和TinyBert☆13Apr 23, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs☆12Nov 7, 2024Updated 2 years ago
- A 3D engine based on WebGPU, including GLTF/OBJ Loader、PBR Render 、HDR Loader and IBL Pre filtered Env Map. Provide a Scene to add 3D obj…☆13Aug 3, 2024Updated 2 years ago
- ☆13Jan 14, 2025Updated last year
- ☆10Jan 27, 2026Updated 9 months ago
- [COLM 2025] Official implementation of μKE - edit LLM knowledge while preserving memory dependencies via Matryoshka-style objectives.☆15Aug 20, 2025Updated last year
- Code for the paper "A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders"☆19Dec 28, 2025Updated 10 months ago
- ☆13Oct 3, 2025Updated last year
Are these results useful?