conftrace_

extraction attack

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

membership inference (2) counterfactual memorization (1) runtime defense (1) canary token (1) knowledge base leakage (1) large language model (1) knowledge deletion (1) autoregressive language model (1) linguistic structure (1) multilingual language model (1)

Papers

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game ACL 2026 The Model’s Language Matters: A Comparative Privacy Analysis of LLMs EACL 2026 Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks ICLR 2024 An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022