Imagen de Portada

Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Gharami, Kanchon, Aluvihare, Hansaka, Moni, Shafika Showkat, Peköz, Berker
Formato:	Preprint
Publicado:	2025
Materias:	Cryptography and Security Artificial Intelligence 68T05, 68Q32, 94A60, I.2.6; I.2.3; I.2.0; D.4.6
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations
por: Okatan, Ayşe S., et al.
Publicado: (2025)

Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study
por: Fachada, Nuno, et al.
Publicado: (2026)

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy
por: Dang, Kieu, et al.
Publicado: (2025)

Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfer
por: Okatan, Ayşe Selin, et al.
Publicado: (2025)

CulinaryCut-VLAP: A Vision-Language-Action-Physics Framework for Food Cutting via a Force-Aware Material Point Method
por: Koh, Hyunseo, et al.
Publicado: (2026)

FT-NCFM: An Influence-Aware Data Distillation Framework for Efficient VLA Models
por: Chen, Kewei, et al.
Publicado: (2025)

On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
por: Shafieinejad, Masoumeh, et al.
Publicado: (2026)

NeuroState-Bench: A Human-Calibrated Benchmark for Commitment Integrity in LLM Agent Profiles
por: Jia, Xiao
Publicado: (2026)

Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior
por: Kim, Dongmin, et al.
Publicado: (2025)

Evaluating Model-Agnostic Meta-Learning on MetaWorld ML10 Benchmark: Fast Adaptation in Robotic Manipulation Tasks
por: Atamuradov, Sanjar
Publicado: (2025)

Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning
por: Stricker, Patrick, et al.
Publicado: (2026)

Thinking Machines: Mathematical Reasoning in the Age of LLMs
por: Asperti, Andrea, et al.
Publicado: (2025)

AI Agents: Evolution, Architecture, and Real-World Applications
por: Krishnan, Naveen
Publicado: (2025)

Constitution or Collapse? Exploring Constitutional AI with Llama 3-8B
por: Zhang, Xue
Publicado: (2025)

Adaptive Minds: Empowering Agents with LoRA-as-Tools
por: Shekar, Pavan C, et al.
Publicado: (2025)

XAutoLM: Efficient Fine-Tuning of Language Models via Meta-Learning and AutoML
por: Estevanell-Valladares, Ernesto L., et al.
Publicado: (2025)

Training a Student Expert via Semi-Supervised Foundation Model Distillation
por: Taghavi, Pardis, et al.
Publicado: (2026)

Ultrahigh-Q chiral resonances empowered by multi-head attention deep learning
por: Zhang, Cong, et al.
Publicado: (2025)

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
por: Chen, Kewei, et al.
Publicado: (2026)

STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery
por: Su, Jiarui, et al.
Publicado: (2026)

Approaches to Semantic Textual Similarity in Slovak Language: From Algorithms to Transformers
por: Radosky, Lukas, et al.
Publicado: (2026)

Solving Zebra Puzzles Using Constraint-Guided Multi-Agent Systems
por: Berman, Shmuel, et al.
Publicado: (2024)

Intersymbolic AI: Interlinking Symbolic AI and Subsymbolic AI
por: Platzer, André
Publicado: (2024)

How much do LLMs learn from negative examples?
por: Hamdan, Shadi, et al.
Publicado: (2025)

Communicative Agents for Slideshow Storytelling Video Generation based on LLMs
por: Fan, Jingxing, et al.
Publicado: (2025)

Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design
por: Pepe, Alberto, et al.
Publicado: (2026)

When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models
por: Basu, Abhinaba
Publicado: (2026)

An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
por: Saini, Saurabh, et al.
Publicado: (2026)

From Noise to Diversity: Random Embedding Injection in LLM Reasoning
por: Kim, Heejun, et al.
Publicado: (2026)

MAcPNN: Mutual Assisted Learning on Data Streams with Temporal Dependence
por: Giannini, Federico, et al.
Publicado: (2026)

NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
por: Breneur, Oleksandr Marchenko, et al.
Publicado: (2026)

Rethinking the Multilingual Reasoning Gap with Layer Swap
por: Lasbordes, Maxence, et al.
Publicado: (2026)

Territory Paint Wars: Diagnosing and Mitigating Failure Modes in Competitive Multi-Agent PPO
por: Singh, Diyansha
Publicado: (2026)

CS-SHRED: Enhancing SHRED for Robust Recovery of Spatiotemporal Dynamics
por: da Silva, Romulo B., et al.
Publicado: (2025)

ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval
por: Syed, Shahram Najam, et al.
Publicado: (2025)

LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning
por: Luijkx, Jelle, et al.
Publicado: (2025)

Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features
por: Chahine, Makram, et al.
Publicado: (2024)

Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity
por: Dominguez, Alejandro Rodriguez, et al.
Publicado: (2025)

Autonomous battery research: Principles of heuristic operando experimentation
por: Lu, Emily, et al.
Publicado: (2025)

Just In Time Transformers
por: Benali, Ahmed Ala Eddine, et al.
Publicado: (2024)