Safeguard
Topic

AI Security

In-depth guides and analysis on ai security from the Safeguard engineering team.

676 articles

AI Security

LLM Unbounded Consumption: Resource Exhaustion Attacks

How attackers exploit token-based pricing and growing context windows to exhaust LLM compute and inflate cloud bills — and the concrete limits that stop them.

Nov 15, 20259 min read
AI Security

LLM Vector and Embedding Weaknesses

Embeddings aren't anonymized math — Vec2Text recovers 92% of text from vectors, and OWASP's LLM08:2025 now names inversion, poisoning, and exposed vector DBs as core AI risks.

Nov 15, 20257 min read
AI Security

LLM System Prompt Leakage

System prompts often hide business logic and secrets. Here's how attackers extract them, real 2023-2024 incidents, and how to stop leaks before they reach production.

Nov 15, 20257 min read
AI Security

Model Theft: Protecting Proprietary LLMs from Extraction ...

A $20 API attack can clone a production LLM's embeddings. Here's how model extraction works, real incidents from LLaMA to DeepSeek, and how to protect proprietary models.

Nov 14, 20257 min read
AI Security

LLM Supply Chain Vulnerabilities

Malicious model files, poisoned datasets, and compromised ML packages are the new software supply chain frontier. Here is how these LLM attacks actually work.

Nov 14, 20257 min read
AI Security

Training Data Poisoning Attacks on Machine Learning Models

A $60 domain purchase or 0.001% of training tokens can silently corrupt an ML model. Here's how training data poisoning attacks work and how to defend against them.

Nov 14, 20257 min read
AI Security

Sensitive Information Disclosure in LLM Applications

From Samsung's ChatGPT leak to RAG pipelines with no access controls, sensitive information disclosure is now a top LLM security risk. Here's how it happens and how to stop it.

Nov 14, 20258 min read
AI Security

Insecure Output Handling in LLM-Integrated Applications

LLM output that reaches a browser, database, or shell unvalidated can trigger XSS, SQL injection, or RCE. Here's how insecure output handling breaks AI apps.

Nov 13, 20258 min read
AI Security

Overreliance on LLM Outputs: A Security Perspective

LLMs hallucinate packages, vulnerability verdicts, and compliance summaries with total confidence. Here's where overreliance on AI outputs creates real security risk—and how to close the gap.

Nov 13, 20257 min read
AI Security

LLM Insecure Plugin Design Vulnerabilities

ChatGPT plugins, LangChain agents, and MCP servers have all shipped insecure plugin flaws exposing accounts and data. Here's how Safeguard defends against them.

Nov 13, 20258 min read
AI Security

LLM Denial of Service Attack Techniques

LLM denial of service attacks exploit sponge prompts, unbounded generation, and denial-of-wallet loops to cripple AI systems without a single exploit.

Nov 13, 20257 min read
AI Security

Excessive Agency in LLM-Powered Applications

Excessive agency turns a bad LLM output into an executed action. From Replit's July 2025 database deletion to Air Canada's chatbot ruling, here's what it is and how to scope it down.

Nov 12, 20258 min read
AI Security (Page 51) — Supply Chain Security Blog | Safeguard