Differences

This shows you the differences between two versions of the page.

--- ml:membership_inference [2025/05/16 04:45] – [In NLP] jmflanig
+++ ml:membership_inference [2026/03/07 22:24] (current) – [Related Pages] jmflanig
@@ Line 4: / Line 4: @@
 ===== In NLP =====
-  * [[https://arxiv.org/pdf/1811.00513.pdf|Song & Shmatikov 2018 - Auditing Data Provenance in Text-Generation Models]] Membership inference attack for language models
+  * **In LLMs**
-  * In LLMs
+    * [[https://arxiv.org/pdf/1811.00513.pdf|Song & Shmatikov 2018 - Auditing Data Provenance in Text-Generation Models]] Membership inference attack for language models
     * [[https://arxiv.org/pdf/2310.16789.pdf|Shi et al 2023 - Detecting Pretraining Data from Large Language Models]]
     * [[https://arxiv.org/pdf/2402.07841.pdf|Duan et al 2024 - Do Membership Inference Attacks Work on Large Language Models?]]
     * [[https://arxiv.org/pdf/2403.0480|Kassem et al 2024 -  Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs]]
-  * Seq2seq
+    * [[https://www.arxiv.org/pdf/2505.18773|Hayes et al 2025 - Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models]]
+  * **Seq2seq**
     * [[https://aclanthology.org/2020.tacl-1.4.pdf|Hisamoto et al 2020 - Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?]]
-  * In general
+  * **In general**
     * [[https://arxiv.org/pdf/2112.03570.pdf|Carlini et al 2021 - Membership Inference Attacks From First Principles]]
@@ Line 17: / Line 18: @@
 ===== Related Pages =====
   * [[Privacy]]
+  * [[nlp:language_model#Extracting Knowledge from Language Models]]