PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
☆28Mar 26, 2025Updated last year
Alternatives and similar repositories for pfi
Users that are interested in pfi are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- PeTAL: Ensuring Access Control Integrity against Data-only Attacks on Linux (ACM CCS 2024)☆18Nov 4, 2024Updated last year
- Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.☆97May 30, 2025Updated last year
- ☆15Mar 9, 2025Updated last year
- TikTag: Breaking ARM's Memory Tagging Extension with Speculative Execution (IEEE S&P 2025)☆87Nov 25, 2024Updated last year
- [VLM-Attack-Survey-2024] Paper list and projects for VLM attacks☆18Feb 12, 2025Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Official Implementation of implicit reference attack☆11Oct 16, 2024Updated last year
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆114Jan 31, 2025Updated last year
- official implementation of [USENIX Sec'25] StruQ: Defending Against Prompt Injection with Structured Queries☆75Nov 10, 2025Updated 7 months ago
- A public repository for the class, "Software Security" at Seoul National University (SNU)☆14May 11, 2021Updated 5 years ago
- Code for "The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction an…☆10Apr 30, 2024Updated 2 years ago
- Codes for our paper "AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems"☆13Dec 13, 2024Updated last year
- ☆16May 18, 2026Updated 3 weeks ago
- Camouflage YOLO - (CAMOLO) trains adversarial patches to confuse the YOLO family of object detectors.☆12Oct 20, 2022Updated 3 years ago
- IRC-like chat program using POSIX advisory lock covert-channel on time namespaces☆23Nov 12, 2025Updated 7 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- [EMNLP 2025 Oral] IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents☆19Sep 16, 2025Updated 8 months ago
- ☆32Apr 2, 2024Updated 2 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☆51May 6, 2026Updated last month
- Official Implementation of wd1☆30Sep 25, 2025Updated 8 months ago
- ☆15Mar 10, 2025Updated last year
- ☆10Sep 14, 2023Updated 2 years ago
- ☆16Sep 17, 2024Updated last year
- The repo for paper: Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models.☆15Dec 16, 2024Updated last year
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆50Updated this week
- 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.
- [EMNLP 2024 Findings] Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information☆13Oct 1, 2024Updated last year
- ☆20May 14, 2025Updated last year
- An omnipowerful personal assistant powered by LLMs, Zapier NLA, and custom actions.☆15Sep 13, 2024Updated last year
- ☆42Feb 26, 2023Updated 3 years ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆51Apr 19, 2026Updated last month
- 🌟 手把手教你在论文中插入代码链接☆25Aug 2, 2025Updated 10 months ago
- Code and data for the ACM CIKM 2024 paper "Adversarial Text Rewriting for Text-aware Recommender Systems"☆12Aug 1, 2024Updated last year
- ☆11Nov 12, 2024Updated last year
- Implement of Implicit Knowledge Extraction Attack.☆23Apr 17, 2026Updated last month
- 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.
- System Audit Architecture with High Event Coverage and Synchronous Log Availability☆19Nov 27, 2024Updated last year
- ☆22Oct 1, 2025Updated 8 months ago
- Adversarial Item Promotion in visually-aware recommenders☆17Sep 3, 2021Updated 4 years ago
- Progent: Securing AI Agents with Privilege Control☆36May 14, 2026Updated 3 weeks ago
- ☆36Jul 27, 2024Updated last year
- [Usenix Security 2025] Official repo of paper PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs☆69Nov 17, 2025Updated 6 months ago
- A neural network for the game Reversi. Trained using a Genetic Algorithm.☆11Feb 6, 2019Updated 7 years ago