Naver sentiment movie corpus

Private Investigator: Extracting Personally Identifiable Information from Large Language Models Using Optimized Prompts

Pytorch implementation of DetectGPT (https://arxiv.org/pdf/2301.11305v1.pdf)

DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

You Only Perturb Once: Bypassing (Robust) Ad-Blockers Using Universal Adversarial Perturbations

Repository for PrimeVul Vulnerability Detection Dataset

CodeXGLUE

🌐 List of free and downloadable top 1M domain list (alexa alternatives) 📊

RICC: Robust Collective Classification of Sybil Accounts

Link: Black-Box Detection of Cross-Site Scripting Vulnerabilities Using Reinforcement Learning

Code and dataset release for our ACSAC 2021 paper titled "Eluding ML-based Adblockers With Actionable Adversarial Examples".

Montage: A Neural Network Language Model-Guided JavaScript Engine Fuzzer

A pytorch adversarial library for attack and defense methods on images and graphs

Structure-based Sybil/Fake account/Spam detection in social networks