liu00222

Open-Prompt-Injection. This repository provides a benchmark for prompt injection attacks and defenses in LLMs

LLM-Based-Personal-Profile-Extraction. This repository contains the code for our USENIX Security'25 paper "Evaluating LLM-based Personal Information Extraction and Countermeasures"

StolenEncoder. Python

PORE-Provably-Robust-Recommender-Systems-against-Data-Poisoning-Attacks. This repository contains the code for our USENIX Security'23 paper "PORE: Provably Robust Recommender Systems against Data Poisoning Attacks"

awesome-llm-security. A curation of awesome tools, documents and projects about LLM Security.

DASH-YMCA-Zooniverse. Python

BadEncoder. Python

agentdojo. A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.