Eresus research, advisory, and security news
We collect writing, advisories, and current-event analysis around AI security, the MCP ecosystem, application security, and real attack chaining here.
Latest Posts
What is a Vector Database? Its Role in AI and LLM Security
How do Vector Databases, the heart of modern AI (LLM) projects, actually work? Discover everything you need to know to prevent data leakage and...
Structuring and Securing AI Microservices in Python (FastAPI)
Why must you transition from monolithic setups to a microservices architecture when exposing AI models to the public? Designing attack-resistant Python...
Why Should We Use Rust for AI-Powered Backend Systems?
When AI assistants are writing half your code, how do you ensure system security? Discover the superiority of the Rust language and its Memory Safety...
Cloud Security: AWS IAM Flaws and One-Click Privilege Escalation
Why do 80% of organizations using Cloud Computing (AWS, Azure) suffer massive breaches strictly through misconfigured Identity and Access Management...
Authentication in AI Applications: LLM Sessions and Data Privacy
Vulnerable JWT management and Context Hijacking attacks in Chatbots, RAG architectures, and AI assistants. Learn how to architect robust Authentication...
The Simplest Bug is the Deadliest: Remote Code Execution (RCE) via Pickle in Machine Learning
Sometimes the simplest bugs are the most dangerous—especially when they’ve been hiding in plain sight. In the world of Machine Learning (ML), data ...
New Perseus Android Banking Malware Monitors Notes Apps for Sensitive Data
A novel Android banking malware dubbed 'Perseus' exploits accessibility services via phishing apps to monitor device screens, harvest sensitive data...
The Overlooked Attack Surface: Hunting 0-Days in AI Model Files
When discussing cybersecurity in Artificial Intelligence, everyone fixates on API security, prompt injections, and web vulnerabilities. Meanwhile, ...
Artificial Intelligence (LLM) Manipulations: Prompt Injection and RAG Poisoning
How does the shiny new ChatGPT clone your company launched fall straight into the hands of cyber attackers? An anatomical breakdown of Direct and...