Papers Model extraction
“Model extraction” 태그가 달린 논문 218편 · 필터 해제
JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols
Large language model (LLM) judges are increasingly used across various evaluation scenarios, making their judgment capabilities valuable intellectual property. However, black-box access exposes these capabilities to mode…
Model extractionCaliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs
We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and th…
Knowledge DistillationModel extractionDECODEM: Data Extraction from Corporate Organizational Documents via Enhanced Methods
Much empirical legal research depends on translating unstructured text into structured variables. In corporate governance research as elsewhere, this translation has traditionally relied on human coding of documents such…
Binary ClassificationModel extractionLet Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
Large language models deployed as commercial APIs are vulnerable to model extraction attacks, while existing defenses either act too late or degrade utility for legitimate users. We propose \textbf{Knowledge Trap}, a def…
Model extractionSciR: A Controllable Benchmark for Scientific Reasoning in LLMs
Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on these in scientific settings is currently out of reach: scientific benchmar…
Model extractionT2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking
Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures. The primary technical challenge lies in ensuring watermark robustness against var…
Model extractionAn Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic
Large language models (LLMs) are increasingly deployed through hosted APIs, making model extraction a practical threat to model ownership and service security. However, individual extraction queries often resemble benign…
Model extractionBAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation
Sequential recommendation systems are widely adopted but often deployed as black-box APIs, which has driven recent interest in model extraction to replicate their capabilities locally. However, the long-tail distribution…
Sequential RecommendationContrastive LearningModel extractionAI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses
Ensuring the protection of Artificial Intelligence (AI) models deployed in military Command and Control (C2) systems and critical infrastructure is essential for maintaining information superiority. Model Extraction Atta…
Model extractionFlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems
Artificial Intelligence (AI)-based Intrusion Detection Systems (IDS) deployed in energy infrastructure are vulnerable to model theft attacks, which allow adversaries to create evasive traffic offline. Current defences ag…
Intrusion DetectionModel extractionA Registry-Bound LLM Pipeline for Evidence-Grounded Trait Extraction across Tropical Plants, Aquatic Species, and Exotic Pets
We describe a registry-bound large-language-model extraction pipeline producing evidence-grounded structured trait records at scale, on cultivated tropical plant, aquatic, and pet species. Four mechanisms render LLM-deri…
Model extractionCan Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
Graph Machine Learning as a Service (GMLaaS) platforms increasingly implement explainability interfaces to meet regulatory transparency requirements. However, this transparency creates exploitable vulnerabilities for mod…
Graph ClassificationModel extractionEMMA: Extracting Multiple physical parameters from Multimodal Data
We introduce EMMA, a physics-informed multimodal framework that recovers all identifiable dynamical parameters of a system directly from raw video, audio, and image-based time-series observations. Unlike prior video-only…
Model extractionAdaptive Probe-based Steering for Robust LLM Jailbreaking
Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious …
Model extractionMADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop
Document processing automation remains a critical challenge in enterprise environments, where traditional manual approaches are labor-intensive and error-prone. We present MADP, a multi-agent architecture that addresses …
Model extractionIdentified-Set Geometry of Distributional Model Extraction under Top-$K$ Censored API Access
Modern LLM APIs often reveal only top-$K$ logit scores and censor the remaining vocabulary. We study the per-position distribution-recovery limits of this access model. For censoring threshold $τ$, the compatible teacher…
Model extractionTrEEStealer: Stealing Decision Trees via Enclave Side Channels
Today, machine learning is widely applied in sensitive, security-related, and financially lucrative applications. Model extraction attacks undermine current business models where a model owner sells model access, e.g., v…
Model extractionA Public Theory of Distillation Resistance via Constraint-Coupled Reasoning Architectures
Knowledge distillation, model extraction, and behavior transfer have become central concerns in frontier AI. The main risk is not merely copying, but the possibility that useful capability can be transferred more cheaply…
Knowledge DistillationModel extractionAI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective
As machine learning (ML) systems expand in both scale and functionality, the security landscape has become increasingly complex, with a proliferation of attacks and defenses. However, existing studies largely treat these…
Model extractionTabKD: Tabular Knowledge Distillation through Interaction Diversity of Learned Feature Bins
Data-free knowledge distillation enables model compression without original training data, critical for privacy-sensitive tabular domains. However, existing methods does not perform well on tabular data because they do n…
Data-free Knowledge DistillationModel CompressionModel extraction