conftrace_

vocabulary partitioning

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) steganographic attack (1) privacy leaking (1) language model security (1) data exfiltration (1) logit balancing (1) privacy leakage (1) text watermarking (1) privacy attack (1)

Papers

SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking ACL 2026 TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent EMNLP 2025