SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks | Paper Citation Record

Observation d64d478d-ad97-4d65-b5c1-fb139eb66485 · outbound

This paper cites https: //oag.ca.gov/privacy/ccpa.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks https: //oag.ca.gov/privacy/ccpa

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.795433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9019e665-db77-4697-b470-cebc4e842151 · outbound

This paper cites https: //gdpr.eu/.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks https: //gdpr.eu/

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.799608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 681bedac-a91c-4f95-87ab-5e0351666c5d · outbound

This paper cites https://github.com/KaiyuanZh/SOFT.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks https://github.com/KaiyuanZh/SOFT

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.802247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fbe55d6a-440a-4674-80df-a7ae22d13f33 · outbound

This paper cites Deep learning with differential privacy.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Deep learning with differential privacy

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.804919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 409cc738-c8dd-4ad8-8dab-9885b7148c8c · outbound

This paper cites Artificial intelligence risk management framework: Generative artificial intelligence profile, 2024.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Artificial intelligence risk management framework: Generative artificial intelligence profile, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.807577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc68fbb-22a8-47dd-845c-b6c6b6b75144 · outbound

This paper cites Tower: An Open Multilingual Large Language Model for Translation-Related Tasks.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Tower: An Open Multilingual Large Language Model for Translation-Related Tasks

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.810332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ba1c93-4b24-4713-b47a-4c5a8363e815 · outbound

This paper cites Large-Scale Differentially Private BERT.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Large-Scale Differentially Private BERT

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.813407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6af2ca3c-78d7-496a-a975-32d350d1a784 · outbound

This paper cites Claude.ai.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Claude.ai

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.816242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d040b645-0088-46f3-a40c-14bf06c2a558 · outbound

This paper cites Private empirical risk minimization: Efficient algo- rithms and tight error bounds.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Private empirical risk minimization: Efficient algo- rithms and tight error bounds

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.818713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd09443-3d4f-4819-aeba-1be0ebb5a07b · outbound

This paper cites On bootstrapping the roc curve.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks On bootstrapping the roc curve

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.821675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81debbcb-920e-402d-9cd5-a06f9378196f · outbound

This paper cites LoRA Learns Less and Forgets Less.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LoRA Learns Less and Forgets Less

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.824450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7adb27eb-4cc6-47c5-b9ed-5f0a1c7af94e · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Pythia: A suite for analyzing large language models across training and scaling

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.827380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 703a5288-161e-49ca-9cd3-4ba37dfb66aa · outbound

This paper cites Language models are few-shot learners.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Language models are few-shot learners

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.830032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fb10549-ed84-4a85-ab6e-dbcd79447c24 · outbound

This paper cites Member- ship inference attacks from first principles.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Member- ship inference attacks from first principles

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.832860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfaadce8-056f-4a35-9da1-b2237f527df8 · outbound

This paper cites Quantifying memorization across neural language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Quantifying memorization across neural language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.835576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 273ea40a-0eb7-41dd-a01b-ef8e5959a684 · outbound

This paper cites Extracting training data from large lan- guage models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Extracting training data from large lan- guage models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.838159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf18839-671c-4c0a-8e08-ce0547554a1d · outbound

This paper cites The janus interface: How fine- tuning in large language models amplifies the privacy risks.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks The janus interface: How fine- tuning in large language models amplifies the privacy risks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.840602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 186aedc7-4214-42f3-bf2a-e65e473ad220 · outbound

This paper cites Label-only membership inference attacks.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Label-only membership inference attacks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.843323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 551f2e13-8b9d-4d51-a949-68ebef9d3ef8 · outbound

This paper cites Reconstruct your previous conversations! com- prehensively investigating privacy leakage risks in con- versations with GPT models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Reconstruct your previous conversations! com- prehensively investigating privacy leakage risks in con- versations with GPT models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.845700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f847fd9-47be-44f9-ba2b-1992b306435c · outbound

This paper cites SaulLM-7B: A pioneering Large Language Model for Law.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks SaulLM-7B: A pioneering Large Language Model for Law

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.848007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c073c910-4be3-4f8a-bfb6-ccb2432706b5 · outbound

This paper cites Blind Baselines Beat Membership Inference Attacks for Foundation Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Blind Baselines Beat Membership Inference Attacks for Foundation Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.850599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 524e6788-58e3-4f04-a937-531dab54a8c6 · outbound

This paper cites Flocks of stochastic parrots: Dif- ferentially private prompt learning for large language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Flocks of stochastic parrots: Dif- ferentially private prompt learning for large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.853155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c2cdb5a-ae76-46ea-a4d2-dafd5572a7d4 · outbound

This paper cites Do membership inference attacks work on large language models? In Conference on Language Modeling (COLM), 2024.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Do membership inference attacks work on large language models? In Conference on Language Modeling (COLM), 2024

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.855475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2527a9af-743b-431b-8d9a-537da256cbc9 · outbound

This paper cites DE-COP: Detecting Copyrighted Content in Language Models Training Data.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks DE-COP: Detecting Copyrighted Content in Language Models Training Data

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.857746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 340682c1-8ee1-4231-836c-0ac54d9cb2eb · outbound

This paper cites Alpaca- farm: A simulation framework for methods that learn from human feedback.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Alpaca- farm: A simulation framework for methods that learn from human feedback

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.860373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1688320-c8f4-4816-9e27-17bd8c3bf010 · outbound

This paper cites Differential privacy.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Differential privacy

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.863139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52990abf-919b-4e9a-9188-1473f90f1196 · outbound

This paper cites The algorithmic foundations of differential privacy.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks The algorithmic foundations of differential privacy

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.865679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1869aac4-9966-4e33-953e-fd66dbd834d5 · outbound

This paper cites Transformer and seq2seq model for paraphrase generation.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Transformer and seq2seq model for paraphrase generation

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.867925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18232bff-95b8-4396-b0ef-3dc4e9322276 · outbound

This paper cites Intentest: Stress testing for in- tent integrity in api-calling llm agents.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Intentest: Stress testing for in- tent integrity in api-calling llm agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.870122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a548407-b609-4614-8a4f-e1849ba0a5de · outbound

This paper cites Membership inference attacks against fine-tuned large language models via self-prompt calibration.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Membership inference attacks against fine-tuned large language models via self-prompt calibration

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.872360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 638a5d41-4de1-4dad-b484-b1bd8adac545 · outbound

This paper cites Data Engineering for Scaling Language Models to 128K Context.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Data Engineering for Scaling Language Models to 128K Context

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.874877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2bb9185-f0fe-4154-9b5e-28b2841fec39 · outbound

This paper cites Zlib compression library.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Zlib compression library

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.993565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f5c46197-138a-4978-baf7-e724847cbef7 · outbound

This paper cites Ppdb: The paraphrase database.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Ppdb: The paraphrase database

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.984192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8d5df65a-a3cc-44fd-ac3f-0c20d2732421 · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.882491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54f72db6-14eb-447d-8c56-42fd6b1d9cb5 · outbound

This paper cites A framework for few-shot language model evaluation, 07 2024.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks A framework for few-shot language model evaluation, 07 2024

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.975633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ec0d90f7-85c5-47cb-b814-6f413ec69466 · outbound

This paper cites How to train long-context language models (effectively).

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks How to train long-context language models (effectively)

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.887563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46486224-f170-4c68-b826-3c34353085f8 · outbound

This paper cites Openllama: An open reproduction of llam, May 2023.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Openllama: An open reproduction of llam, May 2023

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.966940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3d386edc-2ab6-45c6-ab80-d844a8050224 · outbound

This paper cites Pro- filer: Black-box ai-generated text origin detection via context-aware inference pattern analysis.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Pro- filer: Black-box ai-generated text origin detection via context-aware inference pattern analysis

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.956647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fe32efaf-e72c-4b54-8f6a-f7c77a6b3897 · outbound

This paper cites Biscope: Ai-generated text detec- tion by checking memorization of preceding tokens.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Biscope: Ai-generated text detec- tion by checking memorization of preceding tokens

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.946197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b749b6eb-9829-4290-a366-cc84884a8080 · outbound

This paper cites Skewact: Red teaming large language models via activation-skewed adversarial prompt opti- mization.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Skewact: Red teaming large language models via activation-skewed adversarial prompt opti- mization

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.934615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 27b8cf5b-7e74-4222-b0bc-47391e0fbe9e · outbound

This paper cites Learning and evaluating a differentially private pre-trained language model.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Learning and evaluating a differentially private pre-trained language model

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.923685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 05520b23-0f57-4a46-96fa-b1860d6809a4 · outbound

This paper cites Parameter- efficient transfer learning for nlp.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Parameter- efficient transfer learning for nlp

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.912694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 75f8ff0a-85af-47c5-ab78-cb16b322dfcc · outbound

This paper cites LoRA: Low-rank adaptation of large lan- guage models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LoRA: Low-rank adaptation of large lan- guage models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.901010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 93c5ab73-2d2f-49aa-8476-855f16fa53db · outbound

This paper cites LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language mod- els.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LLM-adapters: An adapter family for parameter-efficient fine-tuning of large language mod- els

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.892355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 511de3b9-d4c2-49ca-850f-d28796d01f96 · outbound

This paper cites Membership Inference Attack Susceptibility of Clinical Language Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Membership Inference Attack Susceptibility of Clinical Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.912279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2308bb03-57b8-4b57-b0b3-de4cc823d077 · outbound

This paper cites SWE-bench: Can language models re- solve real-world github issues? In The Twelfth Interna- tional Conference on Learning Representations, 2024.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks SWE-bench: Can language models re- solve real-world github issues? In The Twelfth Interna- tional Conference on Learning Representations, 2024

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.882929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d8ab840b-3cc8-4453-aef9-1155b1b33126 · outbound

This paper cites Scaling Laws for Neural Language Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Scaling Laws for Neural Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.917693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65f68cc7-8b56-43f6-8491-849ed0131e26 · outbound

This paper cites Understanding black- box predictions via influence functions.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Understanding black- box predictions via influence functions

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.874110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4f51fc3c-c292-4c24-a009-bb9d9cd63b40 · outbound

This paper cites One Epoch Is All You Need.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks One Epoch Is All You Need

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.923256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918381ce-8d6e-4a24-a8ef-4ebcf5db27fb · outbound

This paper cites BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.926782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9166fe02-d10f-4b8f-9702-a7dcf7f241d9 · outbound

This paper cites The power of scale for parameter-efficient prompt tuning.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks The power of scale for parameter-efficient prompt tuning

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.865142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b045876b-b50f-4a60-9208-8498658f4a08 · outbound

This paper cites BART: De- noising sequence-to-sequence pre-training for natural language generation, translation, and comprehension.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks BART: De- noising sequence-to-sequence pre-training for natural language generation, translation, and comprehension

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.856197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f2bd7d5-8dcd-49f4-a911-f3d92f15c270 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.934506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afae2c9e-5183-44da-a62a-35f4a677b2d5 · outbound

This paper cites Large Language Models Can Be Strong Differentially Private Learners.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Large Language Models Can Be Strong Differentially Private Learners

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.937446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f4d074e-f227-4423-b215-87df55431d3a · outbound

This paper cites Rethinking Machine Unlearning for Large Language Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Rethinking Machine Unlearning for Large Language Models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.940137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d84ede6c-ef00-4b83-a53e-ee86d603c1e1 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.942847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bb807a7-c5e2-4602-b8a7-a67eb6126d6b · outbound

This paper cites Membership inference attacks by exploiting loss trajectory.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Membership inference attacks by exploiting loss trajectory

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.847472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8feff51e-2c9e-4bb6-825b-0fed7cab320f · outbound

This paper cites Probing Language Models for Pre-training Data Detection.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Probing Language Models for Pre-training Data Detection

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.948188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4bb218e-2a65-4c93-8efb-742ccd31a1ab · outbound

This paper cites A Controlled Study on Long Context Extension and Generalization in LLMs.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks A Controlled Study on Long Context Extension and Generalization in LLMs

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.950893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d39faacf-2e9e-4b34-a25d-d119f847c332 · outbound

This paper cites LLM dataset inference: Did you train on my dataset? In The Thirty-eighth Annual Confer- ence on Neural Information Processing Systems, 2024.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LLM dataset inference: Did you train on my dataset? In The Thirty-eighth Annual Confer- ence on Neural Information Processing Systems, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.838186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation eeb09289-2245-4215-89e0-0611c482c3af · outbound

This paper cites Did the neurons read your book? document-level membership inference for large language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Did the neurons read your book? document-level membership inference for large language models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.828791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 034fbd50-c44c-471b-86e3-32722960d7f6 · outbound

This paper cites SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It).

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.958162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18acc21b-c168-49ed-9d74-5cde10b3e572 · outbound

This paper cites Llama 3.2: Revolutionizing edge ai and vision with open, customizable models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Llama 3.2: Revolutionizing edge ai and vision with open, customizable models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.820305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 02f993dd-2f70-42af-b95c-73f51f50c3c2 · outbound

This paper cites An empirical analysis of memorization in fine-tuned autoregressive language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks An empirical analysis of memorization in fine-tuned autoregressive language models

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.811559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bdeaca95-62a2-452f-8767-b425249e0738 · outbound

This paper cites Scaling data-constrained language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Scaling data-constrained language models

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.801436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 87febaf9-e8e3-4f7c-afa7-1a8222bf6f72 · outbound

This paper cites GPT-4 technical report, 2023.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks GPT-4 technical report, 2023

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.968825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f8c510-f3c8-4517-8faa-f3a94bee219d · outbound

This paper cites Ppdb 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Ppdb 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.785918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d9379f27-284a-4499-80e1-cd7af50a1390 · outbound

This paper cites The text anonymization benchmark (tab): A dedicated cor- pus and evaluation framework for text anonymization.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks The text anonymization benchmark (tab): A dedicated cor- pus and evaluation framework for text anonymization

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.776934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2c64b995-6cd5-43d2-949b-f96d9b92f381 · outbound

This paper cites Estimating training data in- fluence by tracing gradient descent.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Estimating training data in- fluence by tracing gradient descent

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.767842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8cdd2154-5c91-428f-93f1-69461661154d · outbound

This paper cites Building effective agents.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Building effective agents

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.758326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bf4166de-4a5e-4f94-90af-4763b30c3388 · outbound

This paper cites Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.981499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b96059b-c42f-4b0e-81f4-d840077edbc1 · outbound

This paper cites Bait: Large language model backdoor scanning by inverting attack target.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Bait: Large language model backdoor scanning by inverting attack target

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.984257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c2efef-986f-40f6-9425-165614226f3c · outbound

This paper cites Detecting pretraining data from large language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Detecting pretraining data from large language models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.987000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bae9bc7-4434-40c4-8308-1d1cf2b486e6 · outbound

This paper cites Membership inference attacks against machine learning models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Membership inference attacks against machine learning models

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.739290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ab00d880-8ce3-4d8f-9d93-4f298fad1383 · outbound

This paper cites LoRA vs full fine- tuning: An illusion of equivalence.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LoRA vs full fine- tuning: An illusion of equivalence

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.992177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0889e07d-f5cf-4a12-86b0-c6d48903f05a · outbound

This paper cites Stochastic gradient descent with differentially private updates.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Stochastic gradient descent with differentially private updates

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.729919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 49371d4d-2c0f-475d-ae5a-5bbf1960ef90 · outbound

This paper cites $\mu$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks $\mu$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:16.997084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 869951f9-06e8-4933-9cc0-6280cd723635 · outbound

This paper cites Source code foundation models are transferable binary analysis knowledge bases.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Source code foundation models are transferable binary analysis knowledge bases

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.720309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3edf85bf-6f58-4941-abf4-0600f70bf5af · outbound

This paper cites Se- quence to sequence learning with neural networks.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Se- quence to sequence learning with neural networks

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.711366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 28631436-3b2d-4889-820f-dbf87e56ed08 · outbound

This paper cites HydraLoRA: An asymmetric lora ar- chitecture for efficient fine-tuning.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks HydraLoRA: An asymmetric lora ar- chitecture for efficient fine-tuning

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.702546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 370a6c04-0e66-4d26-8dc6-077add980868 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LLaMA: Open and Efficient Foundation Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.008519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 687c688f-1997-4ff2-8c51-76af1d335165 · outbound

This paper cites Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.011809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f081c439-8270-4fbd-bb41-2cbd5e64565d · outbound

This paper cites KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.015325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c6c3da8-2b13-42a8-92da-2f890e1c2679 · outbound

This paper cites A comprehensive survey of continual learning: theory, method and application.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks A comprehensive survey of continual learning: theory, method and application

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.693465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ef11f63f-09a9-4e29-b5f6-2f7829b25807 · outbound

This paper cites Multitask prompt tuning enables parameter-efficient transfer learning.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Multitask prompt tuning enables parameter-efficient transfer learning

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.684816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3ac1799c-1782-42fb-9353-9569638ffdf7 · outbound

This paper cites Machine Unlearning of Features and Labels.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Machine Unlearning of Features and Labels

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.024507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447a4fb0-9746-43f2-9755-6779094dffff · outbound

This paper cites ReCaLL: Membership inference via relative conditional log-likelihoods.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks ReCaLL: Membership inference via relative conditional log-likelihoods

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.674910Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 29533b44-0798-43b0-b81c-52bb5f91ebf1 · outbound

This paper cites Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.030652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 149665d5-5468-4cc4-8ffa-107f384ce2d8 · outbound

This paper cites Prosec: For- tifying code llms with proactive security alignment.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Prosec: For- tifying code llms with proactive security alignment

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.665736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9a4da32a-b945-46e8-add7-f92c764bbf63 · outbound

This paper cites ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs

Reference 90

Resolution: verified exact; local_arxiv, observed 2026-08-07T04:33:17.156317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ccfbd2f4-bf9f-4544-844e-1422cd74e39a · outbound

This paper cites Para- fuzz: An interpretability-driven technique for detecting poisoned samples in nlp.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Para- fuzz: An interpretability-driven technique for detecting poisoned samples in nlp

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.040363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 838173b6-268a-465f-9c65-e204dcb2005d · outbound

This paper cites Privacy risk in machine learning: An- alyzing the connection to overfitting.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Privacy risk in machine learning: An- alyzing the connection to overfitting

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.651715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c5586338-3593-4a77-8e0d-000fe1591a94 · outbound

This paper cites Lofit: Lo- calized fine-tuning on LLM representations.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Lofit: Lo- calized fine-tuning on LLM representations

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.642224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cf9e7a3f-bb11-44ec-af39-d56a74e55e49 · outbound

This paper cites Differentially private fine-tuning of language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Differentially private fine-tuning of language models

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.634028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2d6aadef-23bd-4e53-aa04-07bbcecd29ff · outbound

This paper cites Bag of tricks for training data extraction from language mod- els.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Bag of tricks for training data extraction from language mod- els

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.621730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f56b25a7-67f5-4d05-b978-930ba5445792 · outbound

This paper cites Counterfactual memorization in neural language models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Counterfactual memorization in neural language models

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.612769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 06486087-dd1c-4781-ba8e-977b5d196c03 · outbound

This paper cites Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.059579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c09842f-e619-420a-9d09-bbaf013e431f · outbound

This paper cites Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.063199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503706c5-60dc-4549-9ec3-310e32588f50 · outbound

This paper cites Censor: Defense against gradient in- version via orthogonal subspace bayesian sampling.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks Censor: Defense against gradient in- version via orthogonal subspace bayesian sampling

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T04:33:17.603192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 16f8fd0f-70db-4624-818d-15468c6f285e · outbound

This paper cites LLM Agents Should Employ Security Principles.

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks LLM Agents Should Employ Security Principles

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T04:33:17.074410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers