PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
☆32Mar 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:
- Agent Data Injection (ADI) Attacks☆16Jul 13, 2026Updated 4 months ago
- PeTAL: Ensuring Access Control Integrity against Data-only Attacks on Linux (ACM CCS 2024)☆17Nov 4, 2024Updated 2 years ago
- ☆18Mar 9, 2025Updated last year
- ☆29Aug 31, 2025Updated last year
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆129Jan 31, 2025Updated last year
- 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.
- Progent: Securing AI Agents with Privilege Control☆60Updated this week
- The official implementation of the paper "AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management".☆15Feb 10, 2026Updated 9 months ago
- TikTag: Breaking ARM's Memory Tagging Extension with Speculative Execution (IEEE S&P 2025)☆92Nov 25, 2024Updated last year
- AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents☆40Aug 31, 2025Updated last year
- Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.☆125May 30, 2025Updated last year
- ☆42Mar 12, 2025Updated last year
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆62Jul 16, 2026Updated 4 months ago
- A public repository for the class, "Software Security" at Seoul National University (SNU)☆13May 11, 2021Updated 5 years ago
- ☆15Dec 18, 2025Updated 11 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- DynAuditClaw — A security audit skill that dynamically discovers your OpenClaw agent's real configuration, designs targeted attack scenar…☆15Apr 6, 2026Updated 7 months ago
- ACE: the Abstract-Concrete-Execute security architecture for LLM-integrated app systems.☆16Apr 21, 2026Updated 7 months ago
- ☆18Mar 25, 2026Updated 7 months ago
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆24Jul 2, 2026Updated 4 months ago
- ☆16Sep 17, 2024Updated 2 years ago
- ☆187Jul 2, 2024Updated 2 years ago
- A survey and analysis of source code sandboxing☆17Jun 16, 2025Updated last year
- Codebase of https://arxiv.org/abs/2410.14923☆55Oct 22, 2024Updated 2 years ago
- Official Code for S&P 25 paper "Alleviating the Fear of Losing Alignment in LLM Fine-tuning"☆11May 1, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆61May 6, 2026Updated 6 months ago
- PIForge: An Open Framework for RL-based Prompt Injection Red Teaming.☆43Nov 9, 2026Updated last week
- [S&P 2026] SoK: Evaluating Jailbreak Guardrails for Large Language Models☆51Dec 17, 2025Updated 11 months ago
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆23Jun 12, 2026Updated 5 months ago
- The HitchHiker's Guide to High-Assurance System Observability Protection with Efficient Permission Switches, ACM CCS'24☆11Nov 11, 2024Updated 2 years ago
- Code for "AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents"☆13Sep 29, 2026Updated last month
- ☆10Jan 29, 2026Updated 9 months ago
- Official implementation of the WASP web agent security benchmark☆98Apr 13, 2026Updated 7 months ago
- Claude Code Reverse Engineering Itself☆13Aug 12, 2025Updated last year
- 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.
- Code of paper: xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking"☆18Apr 3, 2026Updated 7 months ago
- ☆103May 27, 2024Updated 2 years ago
- ☆16Aug 7, 2026Updated 3 months ago
- 서울대학교 전기정보공학부 학사 학위논문 LaTeX (비공식) 템플릿☆21Jun 21, 2021Updated 5 years ago
- ☆26Oct 22, 2026Updated last month
- ☆33Oct 23, 2024Updated 2 years ago
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆55Jun 1, 2026Updated 5 months ago
Are these results useful?