PFI: Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
☆31Mar 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)☆17Nov 4, 2024Updated last year
- ☆16Mar 9, 2025Updated last year
- Progent: Securing AI Agents with Privilege Control☆41May 14, 2026Updated 2 months ago
- An Execution Isolation Architecture for LLM-Based Agentic Systems☆120Jan 31, 2025Updated last year
- Flow Integrity Deterministic Enforcement System. Mechanisms for securing AI agents with information-flow control.☆110May 30, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- TikTag: Breaking ARM's Memory Tagging Extension with Speculative Execution (IEEE S&P 2025)☆90Nov 25, 2024Updated last year
- ☆29Aug 31, 2025Updated 10 months ago
- A public repository for the class, "Software Security" at Seoul National University (SNU)☆15May 11, 2021Updated 5 years ago
- AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents☆35Aug 31, 2025Updated 10 months ago
- ☆39Mar 12, 2025Updated last year
- ☆153Jul 2, 2024Updated 2 years ago
- Codebase of https://arxiv.org/abs/2410.14923☆54Oct 22, 2024Updated last year
- ☆16Sep 17, 2024Updated last year
- A survey and analysis of source code sandboxing☆17Jun 16, 2025Updated last year
- 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.
- Multi-dimensional analysis of orthogonal safety directions in LLM alignment☆22Jun 12, 2026Updated last month
- Distribution Preserving Backdoor Attack in Self-supervised Learning☆20Jan 27, 2024Updated 2 years ago
- [NeurIPS 2025] The official implementation of the paper "DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agen…☆58Jul 16, 2026Updated last week
- ☆15Updated this week
- The official implementation of the paper "AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks"☆26Jun 1, 2026Updated last month
- A research workbench for developing and testing attacks against large language models, with a focus on prompt injection vulnerabilities a…☆55Jul 16, 2026Updated last week
- Code for the paper "Defeating Prompt Injections by Design"☆356Jun 20, 2025Updated last year
- Official Implementation of implicit reference attack☆11Oct 16, 2024Updated last year
- Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks☆53May 6, 2026Updated 2 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections☆21Jul 2, 2026Updated 3 weeks ago
- Source code of AsiaCCS'22 paper - RecIPE: Revisiting the Evaluation of Memory Error Defenses☆14Sep 19, 2023Updated 2 years ago
- DynAuditClaw — A security audit skill that dynamically discovers your OpenClaw agent's real configuration, designs targeted attack scenar…☆15Apr 6, 2026Updated 3 months ago
- ☆17Mar 25, 2026Updated 3 months ago
- [Findings of ACL 2023] Bridge the Gap Between CV and NLP! A Optimization-based Textual Adversarial Attack Framework.☆14Aug 27, 2023Updated 2 years ago
- A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.☆678Jun 2, 2026Updated last month
- [S&P 2026] SoK: Evaluating Jailbreak Guardrails for Large Language Models☆44Dec 17, 2025Updated 7 months ago
- Agent Security Bench (ASB)☆273Apr 16, 2026Updated 3 months ago
- Onsite Analysis Infrastructure☆16Jun 23, 2020Updated 6 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- A benchmark and generation framework for malicious agent skills.☆40Jun 10, 2026Updated last month
- Linux kernel source tree patched with Hypervisor-Enforced Kernel Integrity☆13Nov 14, 2023Updated 2 years ago
- [VLM-Attack-Survey-2024] Paper list and projects for VLM attacks☆18Feb 12, 2025Updated last year
- ☆192Oct 31, 2025Updated 8 months ago
- Official implementation of the WASP web agent security benchmark☆98Apr 13, 2026Updated 3 months ago
- ☆15Jun 6, 2023Updated 3 years ago
- [ICML'25] MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents☆36Jul 31, 2025Updated 11 months ago