[NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents".
☆49Apr 19, 2026Updated last month
Alternatives and similar repositories for DRIFT
Users that are interested in DRIFT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".☆76Dec 4, 2025Updated 5 months ago
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆39Aug 4, 2025Updated 9 months ago
- [NeurIPS 2023] The official implementation of paper "Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval" acce…☆28May 14, 2024Updated 2 years ago
- ☆14Jun 6, 2023Updated 2 years ago
- ICCV 2021☆14Oct 6, 2021Updated 4 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.
- ☆18Sep 24, 2020Updated 5 years ago
- ☆23Dec 14, 2023Updated 2 years ago
- IEEE 1588 Precision Time Protocol Simulation☆10May 6, 2019Updated 7 years ago
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- The code of "Image-text Retrieval via Preserving Main Semantic of Vision" in ICME 2023.☆15Dec 25, 2023Updated 2 years ago
- [WWW '25] Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability☆18May 30, 2025Updated 11 months ago
- The official implementation of the paper "AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World …☆50May 2, 2026Updated 2 weeks ago
- This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning…☆19Jun 7, 2023Updated 2 years ago
- Divide-and-Conquer Attack: Harnessing the Power of LLM to Bypass the Censorship of Text-to-Image Generation Mode☆17Feb 16, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A simple pytorch implementation of baseline based-on CLIP for Image-text Matching.☆19May 25, 2023Updated 2 years ago
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning☆21Jan 24, 2024Updated 2 years ago
- Awesome Video Coding Papers☆13Feb 19, 2025Updated last year
- ☆40Oct 2, 2024Updated last year
- [ICLR 2026] The official code for "Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models"☆26Feb 7, 2026Updated 3 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆113Jan 31, 2025Updated last year
- Code repository for the paper --- [USENIX Security 2023] Towards A Proactive ML Approach for Detecting Backdoor Poison Samples☆30Jul 11, 2023Updated 2 years ago
- Seeing What You Miss: Vision-Language Pre-training with Semantic Completion Learning☆20Dec 21, 2023Updated 2 years ago
- ☆32Sep 3, 2024Updated last year
- 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.
- Codes for our paper "AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems"☆13Dec 13, 2024Updated last year
- Evaluation code for confidential virtual machines (AMD SEV-SNP / Intel TDX)☆16Mar 12, 2026Updated 2 months ago
- The code of the paper of "A Differentiable Semantic Metric Approximation in Probabilistic Embedding for Cross-Modal Retrieval" accepted b…☆19Jan 16, 2024Updated 2 years ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆36Jan 9, 2023Updated 3 years ago
- Oblivious HTTP☆25Jan 2, 2024Updated 2 years ago
- Camouflage YOLO - (CAMOLO) trains adversarial patches to confuse the YOLO family of object detectors.☆12Oct 20, 2022Updated 3 years ago
- Code for the paper Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation (CVPR 2023).☆34May 26, 2023Updated 2 years ago
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆18Sep 16, 2025Updated 8 months ago
- Demo code for the paper: One Thing to Fool them All: Generating Interpretable, Universal, and Physically-Realizable Adversarial Features☆12Nov 30, 2023Updated 2 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.
- ☆15Mar 9, 2025Updated last year
- 该项目使用Go语言编写的视频 网站后端框架 ，使用GO+Gin+Gorm+Redis框架。GoLang Video Back-End ,The projectis make GoLang program,this project uses GO+Gin+Gorm+Redis.…☆14Aug 11, 2022Updated 3 years ago
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆48May 6, 2026Updated 2 weeks ago
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆71Oct 23, 2024Updated last year
- [NAACL Findings 2025] This is the official repository for SusGen-GPT.☆18Jan 23, 2025Updated last year
- ☆12Mar 24, 2023Updated 3 years ago
- A static website for a Chatbot with Azure OpenAI, Azure Text to Speech Services and Live2D☆13Sep 4, 2024Updated last year