SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models

• URL: http://arxiv.org/abs/2604.01147v1
• Date: Wed, 01 Apr 2026 17:03:58 GMT
• Title: SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models
• Abstract summary: We propose SERSEM, a novel white-box attack framework that suppresses uninformative syntactical boilerplate to amplify memorization signals.<n>Our findings demonstrate that focusing on human-centric coding anomalies provides a significantly more robust indicator of verbatim memorization than sequence-level probability averages.
• Score: 1.327416973220814
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As Large Language Models (LLMs) for code increasingly utilize massive, often non-permissively licensed datasets, evaluating data contamination through Membership Inference Attacks (MIAs) has become critical. We propose SERSEM (Selective Entropy-Weighted Scoring for Membership Inference), a novel white-box attack framework that suppresses uninformative syntactical boilerplate to amplify specific memorization signals. SERSEM utilizes a dual-signal methodology: first, a continuous character-level weight mask is derived through static Abstract Syntax Tree (AST) analysis, spellchecking-based multilingual logic detection, and offline linting. Second, these heuristic weights are used to pool internal transformer activations and calibrate token-level Z-scores from the output logits. Evaluated on a 25,000-sample balanced dataset, SERSEM achieves a global AUC-ROC of 0.7913 on the StarCoder2-3B model and 0.7867 on the StarCoder2-7B model, consistently outperforming the implemented probability-based baselines Loss, Min-K% Prob, and PAC. Our findings demonstrate that focusing on human-centric coding anomalies provides a significantly more robust indicator of verbatim memorization than sequence-level probability averages.

Related papers

• Modeling Normal Is All You Need: Joint Latent Clustering for Anomaly Detection in Multimodal Cyber-Physical Systems [47.027290803102666]
  Normal behaviour is the union of many imbalanced, curved, thin-fringed operating regimes.<n>We model the normal law with a jointly learned latent representation plus explicit Gaussian-mixture mode clustering.<n>We evaluate under a deliberately fair protocol: raw point-wise metrics with no point adjustment, a trivial-detector difficulty split, prevalence-matched F1, and train-normal-only calibration.
  arXiv  Detail & Related papers  (2026-07-07T10:10:00Z)
• Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models [59.51249894128724]
  Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration.<n>We propose ADAS, a training-free reranking rule for parallel masked diffusion decoding.
  arXiv  Detail & Related papers  (2026-06-09T13:17:27Z)
• Membership Inference Attacks against Large Audio Language Models [50.84901010528239]
  We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (LALMs)<n>Using a multi-modal blind baseline based on textual, spectral, and prosodic features, we demonstrate that common speech datasets exhibit near-perfect train/test separability.<n>These findings establish a principled standard for auditing LALMs beyond spurious correlations.
  arXiv  Detail & Related papers  (2026-03-30T12:45:28Z)
• Beyond Raw Detection Scores: Markov-Informed Calibration for Boosting Machine-Generated Text Detection [105.14032334647932]
  Machine-generated texts (MGTs) pose risks such as disinformation and phishing, highlighting the need for reliable detection.<n> Metric-based methods, which extract statistically distinguishable features of MGTs, are often more practical than complex model-based methods that are prone to overfitting.<n>We propose a Markov-informed score calibration strategy that models two relationships of context detection scores that may aid calibration.
  arXiv  Detail & Related papers  (2026-02-08T16:06:12Z)
• Refining Decision Boundaries In Anomaly Detection Using Similarity Search Within the Feature Space [3.3202103799131795]
  We introduce SDA2E, a Sparse Dual Adversarial Attention-based AutoEncoder designed to learn compact and discriminative latent representations from imbalanced, high-dimensional data.<n>We propose a similarity-guided active learning framework that integrates three novel strategies to refine decision boundaries efficiently.<n>We evaluate SDA2E extensively across 52 imbalanced datasets, including multiple DARPA Transparent Computing scenarios, and benchmark it against 15 state-of-the-art anomaly detection methods.
  arXiv  Detail & Related papers  (2026-02-02T23:55:08Z)
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective [85.06838178922791]
  Reinforcement Learning (RL) has proven highly effective for autoregressive language models.<n>But adapting these methods to diffusion large language models (dLLMs) presents fundamental challenges.<n>We propose a principled RL framework that treats entire sequence generation as a single action and uses the ELBO as a tractable sequence-level likelihood proxy.
  arXiv  Detail & Related papers  (2025-12-03T13:05:32Z)
• Self-Paced Learning for Images of Antinuclear Antibodies [17.410595974529457]
  Antinuclear antibody (ANA) testing is a crucial method for diagnosing autoimmune disorders, including lupus, Sjgren's syndrome, and scleroderma.<n>ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations.<n>In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using microscope images without manual preprocessing.
  arXiv  Detail & Related papers  (2025-11-26T15:50:03Z)
• User-Based Sequential Modeling with Transformer Encoders for Insider Threat Detection [0.005755004576310333]
  Insider threat detection presents unique challenges due to the authorized status of malicious actors.<n>Existing machine learning methods treat user activity as isolated events, thereby failing to leverage sequential dependencies in user behavior.<n>We propose a User-Based Sequencing (UBS) methodology, transforming the CERT insider threat dataset into structured temporal sequences suitable for deep sequential modeling.
  arXiv  Detail & Related papers  (2025-06-30T00:47:31Z)
• Co-training for Low Resource Scientific Natural Language Inference [65.37685198688538]
  We propose a novel co-training method that assigns weights based on the training dynamics of the classifiers to the distantly supervised labels. By assigning importance weights instead of filtering out examples based on an arbitrary threshold on the predicted confidence, we maximize the usage of automatically labeled data. The proposed method obtains an improvement of 1.5% in Macro F1 over the distant supervision baseline, and substantial improvements over several other strong SSL baselines.
  arXiv  Detail & Related papers  (2024-06-20T18:35:47Z)
• MAPL: Memory Augmentation and Pseudo-Labeling for Semi-Supervised Anomaly Detection [0.0]
  A new meth-odology for detecting surface defects in in-dustrial settings is introduced, referred to as Memory Augmentation and Pseudo-Labeling(MAPL)<n>The methodology first in-troduces an anomaly simulation strategy, which significantly improves the model's ability to recognize rare or unknown anom-aly types.<n>An end-to-end learning framework is employed by MAPL to identify the abnormal regions directly from the input data.
  arXiv  Detail & Related papers  (2024-05-10T02:26:35Z)
• GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models [60.48306899271866]
  We present a new framework, called GREAT Score, for global robustness evaluation of adversarial perturbation using generative models. We show high correlation and significantly reduced cost of GREAT Score when compared to the attack-based model ranking on RobustBench. GREAT Score can be used for remote auditing of privacy-sensitive black-box models.
  arXiv  Detail & Related papers  (2023-04-19T14:58:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.