The implementation for paper "UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models".
☆17Jul 3, 2025Updated last year
Alternatives and similar repositories for UniGuardian
Users that are interested in UniGuardian are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An easy-to-run implementation for finetuning large language models (LLMs) such as llama and gemma, supporting full parameter finetuning, …☆12May 6, 2024Updated 2 years ago
- RapidIn: Scalable Influence Estimation for Large Language Models (LLMs). The implementation for paper "Token-wise Influential Training Da…☆22Mar 10, 2026Updated 6 months ago
- This script can download the HCP dataset automatically from amazon s3 browser by using python. You can download tfMRI, rfMRI, dfMRI, MEG …☆25Sep 8, 2020Updated 6 years ago
- This repository provides the official implementation of VTBench, a benchmark designed to evaluate the performance of visual tokenizers (V…☆36Jul 30, 2025Updated last year
- It is a repo about Brain Decoding Analysis.☆10Sep 11, 2020Updated 6 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- This repo includes the experiment codes and experiment results for the Skip Attention Module (SAM). The SAM is a parameter-free attention…☆13Jan 20, 2022Updated 4 years ago
- The official implementation for the paper "Agent-Omni: Test-Time Multimodal Reasoning via Model Coordination for Understanding Anything".☆23Nov 5, 2025Updated 11 months ago
- This is the official Gtihub repo for our paper: "BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Lang…☆24Jul 3, 2024Updated 2 years ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆33Sep 19, 2025Updated last year
- Code repository for our paper, "Medical Large Language Models are Vulnerable to Data Poisoning Attacks" (Nature Medicine, 2024).☆13Jan 5, 2025Updated last year
- ☆31Jan 30, 2026Updated 8 months ago
- Code for "Unlearning Traces the Influential Training Data of Language Models"☆13Jun 13, 2024Updated 2 years ago
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆39Jul 31, 2025Updated last year
- A repo for LLM jailbreak☆14Sep 5, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- An original implementation of gradient boosting from scratch☆11Jun 2, 2022Updated 4 years ago
- Code associated with ICML (2024). "Defense against Backdoor Attack on Pre-trained Language Models via Head Pruning and Attention Normaliz…☆11Feb 22, 2026Updated 7 months ago
- Code for the paper: Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions☆12Mar 13, 2024Updated 2 years ago
- [ICLR'26 Oral] RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments☆65Feb 9, 2026Updated 8 months ago
- Two-party Privacy-preserving Neural Network Training using Split Learning and Homomorphic Encryption (CKKS Scheme)☆13Sep 23, 2025Updated last year
- [NeurIPS'24] Official implement of "PrivCirNet: Efficient Private Inference via Block Circulant Transformation"☆14Feb 26, 2026Updated 7 months ago
- The code implementation of GraCeFul (Accepted in COLING 2025)☆14Jan 27, 2025Updated last year
- ☆18Oct 2, 2024Updated 2 years ago
- ☆14May 23, 2023Updated 3 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.
- Official repository of the paper "InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection"☆16Nov 13, 2025Updated 10 months ago
- Code for the paper "BadPrompt: Backdoor Attacks on Continuous Prompts"☆41Jul 8, 2024Updated 2 years ago
- Code release for MPCViT accepted by ICCV 2023☆17Jan 6, 2025Updated last year
- Implementation for the protocols described in https://eprint.iacr.org/2023/1700☆14Apr 29, 2026Updated 5 months ago
- [ArXiv 2025] Denial-of-Service Poisoning Attacks on Large Language Models☆23Oct 22, 2024Updated last year
- ☆19Feb 25, 2024Updated 2 years ago
- tensorflow implementation of cnn localization project by CSAIL@MIT (CVPR'16)☆17Sep 18, 2017Updated 9 years ago
- ☆16Feb 26, 2025Updated last year
- PyTorch implementation of Stereopagnosia: Fooling Stereo Networks with Adversarial Perturbations (in AAAI 2021)☆13Mar 20, 2022Updated 4 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Internal Consistency Regularization (CROW) for LLM Backdoor Elimination - Paper accepted to ICML 2025☆16May 6, 2025Updated last year
- Curvature Graph Network☆19Jul 1, 2020Updated 6 years ago
- ☆19Nov 27, 2024Updated last year
- ProbeLLM: Automating Principled Diagnosis of LLM Failures☆18Feb 11, 2026Updated 7 months ago
- Privacy-Preserving Verifiable Neural Network Inference Service (ACSAC 2024)☆19Sep 6, 2025Updated last year
- One-shot handwritten text synthesis with Vision Transformers for English and Vietnamese.☆25Aug 3, 2026Updated 2 months ago
- TextGuard: Provable Defense against Backdoor Attacks on Text Classification☆15Nov 7, 2023Updated 2 years ago