conftrace_

sensitive data leakage

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

cipher substitution (1) large language model (1) model context protocol (1) data security (1) polyalphabetic cipher (1) adversarial prompt injection (1) font injection (1) safety mechanism bypass (1) data encryption (1) language model pretraining (1)

Papers

Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data IJCNLP 2025 Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Models EMNLP 2025