Differences

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

--- ml:membership_inference [2024/03/01 23:53] – created jmflanig
+++ ml:membership_inference [2026/03/07 22:24] (current) – [Related Pages] jmflanig
@@ Line 1: / Line 1: @@
 ====== Membership Inference ======
-  * Overviews
+===== Overviews =====
-    * [[https://arxiv.org/pdf/2103.07853.pdf|Hu et al 2021 - Membership Inference Attacks on Machine Learning: A Survey]]
+  * [[https://arxiv.org/pdf/2103.07853.pdf|Hu et al 2021 - Membership Inference Attacks on Machine Learning: A Survey]]
-  * In NLP
+===== In NLP =====
+  * **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
-    * In LLMs
+    * [[https://arxiv.org/pdf/2310.16789.pdf|Shi et al 2023 - Detecting Pretraining Data from Large 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/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]]
-      * [[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?]]
+  * **Seq2seq**
-    * In general
+    * [[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?]]
-      * [[https://arxiv.org/pdf/2112.03570.pdf|Carlini et al 2021 - Membership Inference Attacks From First Principles]]
+  * **In general**
+    * [[https://arxiv.org/pdf/2112.03570.pdf|Carlini et al 2021 - Membership Inference Attacks From First Principles]]
 ===== Related Pages =====
+  * [[Privacy]]
+  * [[nlp:language_model#Extracting Knowledge from Language Models]]