leolee99 / PIGuardView external linksLinks
[ACL 2025] The official implementation of the paper "PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free".
☆59Dec 4, 2025Updated 2 months ago
Alternatives and similar repositories for PIGuard
Users that are interested in PIGuard are comparing it to the libraries listed below
Sorting:
- 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
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆35Feb 4, 2026Updated last week
- A simple pytorch implementation of baseline based-on CLIP for Image-text Matching.☆18May 25, 2023Updated 2 years ago
- ☆17Jul 26, 2025Updated 6 months ago
- Code for our NAACL2025 accepted paper: Attention Tracker: Detecting Prompt Injection Attacks in LLMs☆20Sep 19, 2025Updated 4 months ago
- [ACL 2025] The official code for "AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection".☆32Aug 4, 2025Updated 6 months ago
- [COLM 2024] JailBreakV-28K: A comprehensive benchmark designed to evaluate the transferability of LLM jailbreak attacks to MLLMs, and fur…☆85May 9, 2025Updated 9 months ago
- The code of the paper "Negative Pre-aware for Noisy Cross-modal Matching" in AAAI 2024.☆29Jul 2, 2025Updated 7 months ago
- Red Queen Dataset and data generation template☆25Dec 26, 2025Updated last month
- [ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents☆29Jun 24, 2025Updated 7 months ago
- Independent robustness evaluation of Improving Alignment and Robustness with Short Circuiting☆18Apr 15, 2025Updated 9 months ago
- Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Technique☆18Aug 22, 2024Updated last year
- Detection of malicious prompts used to exploit large language models (LLMs) by leveraging supervised machine learning classifiers.☆19Oct 30, 2024Updated last year
- Every practical and proposed defense against prompt injection.☆630Feb 22, 2025Updated 11 months ago
- Prompt Injection Attacks against GPT-4, Gemini, Azure, Azure with Jailbreak☆29Oct 8, 2024Updated last year
- The official implementation of our pre-print paper "Automatic and Universal Prompt Injection Attacks against Large Language Models".☆68Oct 23, 2024Updated last year
- The official implementation of paper "Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval" accepted by NeurIPS…☆27May 14, 2024Updated last year
- A benchmark for prompt injection detection systems.☆159Dec 16, 2025Updated last month
- Repo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"☆84Jul 24, 2025Updated 6 months ago
- A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.☆71May 22, 2025Updated 8 months ago
- Code and data to go with the Zhu et al. paper "An Objective for Nuanced LLM Jailbreaks"☆36Dec 18, 2024Updated last year
- [CCS 2024] Optimization-based Prompt Injection Attack to LLM-as-a-Judge☆39Sep 17, 2025Updated 4 months ago
- Test LLMs against jailbreaks and unprecedented harms☆40Oct 19, 2024Updated last year
- ☆12Jul 25, 2018Updated 7 years ago
- Official implementation of the WASP web agent security benchmark☆67Aug 12, 2025Updated 6 months ago
- ☆10Updated this week
- ☆14May 1, 2023Updated 2 years ago
- The Pair App is employed by the Agency of Learning for team management and communication.☆10Apr 13, 2024Updated last year
- 2020湖南省第一届人工智能大赛参赛作品☆11Feb 17, 2022Updated 3 years ago
- Program uses cv2 to display many streams from cameras, web pages, local files☆14Jan 31, 2021Updated 5 years ago
- ☆13Jan 16, 2025Updated last year
- Precision Knowledge Editing (PKE): A novel method to reduce toxicity in LLMs while preserving performance, with robust evaluations and ha…☆11Nov 26, 2024Updated last year
- A static website for a Chatbot with Azure OpenAI, Azure Text to Speech Services and Live2D☆13Sep 4, 2024Updated last year
- Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs☆106Dec 2, 2024Updated last year
- Reduction Server in Rust☆13Apr 9, 2024Updated last year
- Q&A dataset for many-shot jailbreaking☆14Jul 19, 2024Updated last year
- Panda - is a set of utilities used to research how PsExec encrypts its traffic.☆12Apr 20, 2021Updated 4 years ago
- ☆10Jul 5, 2016Updated 9 years ago
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆20Jul 31, 2025Updated 6 months ago