Invisible Text Attacks: Bypassing Human Audits in AI Pipelines
A deep dive into how adversaries exploit PDF XRef tables and DOM rendering layers to hide prompt injections from humans while guaranteeing LLM execution.
4 docs tagged with "steganography"
View all tagsSecuring RAG Pipelines: Deep Document Sanitization and AST Analysis
Advanced architectural strategies for securing Retrieval-Augmented Generation (RAG) pipelines against Indirect Prompt Injection, zero-width Unicode steganography, and SSRF payloads.
Steganography 101 for AI
Attackers are hiding prompt injections in zero-width spaces and tabs. Learn how Whitespace Steganography works and why regex is the best tool to catch it.
Steganography in AI: Hiding Malware in Jupyter Chart Pixels
Detecting advanced steganography attacks where adversaries hide executable payloads or Prompt Injections inside the Least Significant Bits (LSB) of images.