Active Authentication via Korean Keystrokes Under Varying LLM Assistance and Cognitive Contexts

• URL: http://arxiv.org/abs/2509.24807v1
• Date: Mon, 29 Sep 2025 13:57:16 GMT
• Title: Active Authentication via Korean Keystrokes Under Varying LLM Assistance and Cognitive Contexts
• Abstract summary: We evaluate keystroke-based authentication in Korean across three realistic typing scenarios.<n>We show that the system maintains reliable performance across varying LLM usages and cognitive contexts.
• Score: 3.091662349810693
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Keystroke dynamics is a promising modality for active user authentication, but its effectiveness under varying LLM-assisted typing and cognitive conditions remains understudied. Using data from 50 users and cognitive labels from Bloom's Taxonomy, we evaluate keystroke-based authentication in Korean across three realistic typing scenarios: bona fide composition, LLM content paraphrasing, and transcription. Our pipeline incorporates continuity-aware segmentation, feature extraction, and classification via SVM, MLP, and XGB. Results show that the system maintains reliable performance across varying LLM usages and cognitive contexts, with Equal Error Rates ranging from 5.1% to 10.4%. These findings demonstrate the feasibility of behavioral authentication under modern writing conditions and offer insights into designing more context-resilient models.

Related papers

• Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge [21.86609553205461]
  Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge.<n>We introduce TKFQA, a factuality consistency benchmark comprising 10,130 question-answering (QA) pairs grounded in tables, texts, and knowledge graphs (KGs)<n>Each example is constructed from an explicit counterfactual reasoning chain, enabling the joint evaluation of answer correctness, reasoning-chain accuracy, and robustness to different input-order.
  arXiv  Detail & Related papers  (2026-08-08T00:46:32Z)
• When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking [0.41998444721319217]
  We conduct an empirical investigation into the efficacy of pre-trained Large Language Models for password cracking using synthetic user profiles.<n>We evaluate the performance of state-of-the-art open-source LLMs by prompting them to generate plausible passwords based on structured user attributes.<n>Our results, measured using Hit@1, Hit@5, and Hit@10 metrics, reveal consistently poor performance, with all models achieving less than 1.5% accuracy at Hit@10.
  arXiv  Detail & Related papers  (2025-10-18T02:15:28Z)
• Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation [59.40886078302025]
  Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs.<n>Yet, the extent to which generated tokens depend on visual modalities remains poorly understood.<n>We present a lightweight black-box framework for explaining autoregressive token generation in MLLMs.
  arXiv  Detail & Related papers  (2025-09-26T15:38:42Z)
• LLM-Assisted Cheating Detection in Korean Language via Keystrokes [1.9344365651682767]
  This paper presents a keystroke-based framework for detecting LLM-assisted cheating in Korean.<n>Our dataset includes 69 participants who completed writing tasks under three conditions: Bona fide writing, paraphrasing ChatGPT responses, and transcribing ChatGPT responses.
  arXiv  Detail & Related papers  (2025-07-29T20:59:03Z)
• Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning [67.90033766878962]
  Self-supervised feature learning (RL) often rely on information-theoretic principles, termed mutual information skill learning (MISL)<n>Our work investigates MISL through the lens of identifiable representation learning.<n>We prove that Contrastive Successor Features (CSF) can provably recover the environment's ground-truth features up to a linear transformation.
  arXiv  Detail & Related papers  (2025-07-19T20:48:46Z)
• When Meaning Stays the Same, but Models Drift: Evaluating Quality of Service under Token-Level Behavioral Instability in LLMs [4.265831047857601]
  We investigate how large language models respond to prompts that differ only in their token-level realization but preserve the same semantic intent.<n>We propose Prompt-Based Semantic Shift (PBSS), a diagnostic framework for measuring behavioral drift in LLMs under semantically equivalent prompt rewordings.
  arXiv  Detail & Related papers  (2025-06-11T18:26:32Z)
• An Empirical Study of Federated Prompt Learning for Vision Language Model [89.2963764404892]
  This paper systematically investigates the behavioral differences between language prompt learning (VPT) and vision prompt learning (VLM)<n>We evaluate the impact of various FL and prompt configurations, such as client scale, aggregation strategies, and prompt length, to assess the robustness of Federated Prompt Learning (FPL)
  arXiv  Detail & Related papers  (2025-05-29T03:09:15Z)
• Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Models [16.23854525619129]
  Language models (LMs) show promise for vulnerability detection but struggle with long, real-world code due to sparse and uncertain vulnerability locations.<n>We propose FocusVul, a model-agnostic framework that improves LM-based vulnerability detection by learning to select sensitive context.
  arXiv  Detail & Related papers  (2025-05-23T04:41:54Z)
• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system.<n>It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods [56.073335779595475]
  We propose ReCaLL (Relative Conditional Log-Likelihood) to detect pretraining data by leveraging conditional language modeling capabilities.<n>Our empirical findings show that conditioning member data on non-member prefixes induces a larger decrease in log-likelihood compared to non-member data.<n>We conduct comprehensive experiments and show that ReCaLL achieves state-of-the-art performance on the WikiMIA dataset.
  arXiv  Detail & Related papers  (2024-06-23T00:23:13Z)
• Do LLMs Dream of Ontologies? [13.776194387957617]
  Large Models Language (LLMs) have demonstrated remarkable memorization across diverse natural language processing tasks.<n>This paper investigates the extent to which general-purpose LLMs correctly reproduce concept identifier (ID)-label associations from publicly available resources.
  arXiv  Detail & Related papers  (2024-01-26T15:10:23Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)

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.