Olares: An Open-Source Personal Cloud to Reclaim Your Data

Powerful search page powered by LLMs and SearXNG

A curated list of academic events on AI Security & Privacy

[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text

When the stakes are high, intelligence is only half the equation - reliability is the other ⚠️

OfflineAI is an artificial intelligence that operates offline and uses machine learning to perform various tasks based on the code provided. It is built using two powerful AI models by Mistral AI.

[ICCV 2025] Geminio is a VLM-powered gradient inversion attack in federated learning (FL). It allows the adversary (the FL server) to describe the data of value and reconstruct the victim client's private data matching the description.

The LLM Unlearning repository is an open-source project dedicated to the concept of unlearning in Large Language Models (LLMs). It aims to address concerns about data privacy and ethical AI by exploring and implementing unlearning techniques that allow models to forget unwanted or sensitive data. This ensures that AI models comply with privacy.

Comprehensive taxonomy of AI security vulnerabilities, LLM adversarial attacks, prompt injection techniques, and machine learning security research. Covers 71+ attack vectors including model poisoning, agentic AI exploits, and privacy breaches.

awesome list of multi-agent security resources

A Privacy-First Scripting Language that gives you control over Al visibility and context sharing.

Machine Learning Safety

Un dépot centralisé pour partager des idées et des implémentations de techniques en sécurité de l'IA