Pith. sign in

REVIEW 4 cited by

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.00154 v2 pith:RAZAQIGF submitted 2024-10-31 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords membershipworkdocumentsinferencellmsrecentwhenattacks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Membership inference attacks (MIA) attempt to verify the membership of a given data sample in the training set for a model. MIA has become relevant in recent years, following the rapid development of large language models (LLM). Many are concerned about the usage of copyrighted materials for training them and call for methods for detecting such usage. However, recent research has largely concluded that current MIA methods do not work on LLMs. Even when they seem to work, it is usually because of the ill-designed experimental setup where other shortcut features enable "cheating." In this work, we argue that MIA still works on LLMs, but only when multiple documents are presented for testing. We construct new benchmarks that measure the MIA performances at a continuous scale of data samples, from sentences (n-grams) to a collection of documents (multiple chunks of tokens). To validate the efficacy of current MIA approaches at greater scales, we adapt a recent work on Dataset Inference (DI) for the task of binary membership detection that aggregates paragraph-level MIA features to enable MIA at document and collection of documents level. This baseline achieves the first successful MIA on pre-trained and fine-tuned LLMs.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Implicit Reasoning Steering via Concept Chaining

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Reinforcement-learning-optimized concept-chain paragraphs covertly steer language-model multiple-choice preferences after continued pretraining, with far lower detectability than direct paraphrases.

  2. What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests

    cs.CL 2025-07 conditional novelty 6.0 of 10

    WikiMem, a Wikidata-derived canary dataset and a calibrated NLL-ranking metric, identifies which human-fact associations an LLM has memorized, with higher rates for famous people and larger models.

  3. SECNEURON: Reliable and Flexible Abuse Control in Local LLMs via Hybrid Neuron Encryption

    cs.CR 2025-06 conditional novelty 6.0 of 10

    SECNEURON uses per-neuron AES encryption plus attribute-based key management so a locally deployed LLM can be selectively decrypted to allow only authorized tasks and prune unauthorized capabilities.

  4. Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis

    cs.LG 2025-09 conditional novelty 5.0 of 10

    A random forest trained on transformer hidden-state and attention features detects training data membership with about 0.83 average AUC, far above output-based attacks.

Pith tools