Imagen de Portada

Kolmogorov Complexity Bounds for LLM Steganography and a Perplexity-Based Detection Proxy

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Shportko, Andrii
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Paraphrasing Attack Resilience of Various AI-Generated Text Detection Methods
por: Shportko, Andrii, et al.
Publicado: (2026)

Don't Forget It! Conditional Sparse Autoencoder Clamping Works for Unlearning
por: Khoriaty, Matthew, et al.
Publicado: (2025)

Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
por: Ankner, Zachary, et al.
Publicado: (2024)

Minibatch Optimal Transport and Perplexity Bound Estimation in Discrete Flow Matching
por: Haxholli, Etrit, et al.
Publicado: (2024)

Generalization Bounds and Model Complexity for Kolmogorov-Arnold Networks
por: Zhang, Xianyang, et al.
Publicado: (2024)

Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models
por: Haxholli, Etrit, et al.
Publicado: (2025)

Token-Level Adversarial Prompt Detection Based on Perplexity Measures and Contextual Information
por: Hu, Zhengmian, et al.
Publicado: (2023)

Low-Perplexity LLM-Generated Sequences and Where To Find Them
por: Wuhrmann, Arthur, et al.
Publicado: (2025)

Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
por: Wan, Guangnian, et al.
Publicado: (2026)

Rethinking Perplexity: Revealing the Impact of Input Length on Perplexity Evaluation in LLMs
por: Cheng, Letian, et al.
Publicado: (2026)

Accelerated Preference Elicitation with LLM-Based Proxies
por: Huang, David, et al.
Publicado: (2025)

Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training
por: Liu, Lei, et al.
Publicado: (2025)

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
por: Chen, Sirui, et al.
Publicado: (2026)

CVKAN: Complex-Valued Kolmogorov-Arnold Networks
por: Wolff, Matthias, et al.
Publicado: (2025)

Detecting Proxy Gaming in RL and LLM Alignment via Evaluator Stress Tests
por: Shihab, Ibne Farabi, et al.
Publicado: (2025)

Neural Weight Norm = Kolmogorov Complexity
por: Musat, Tiberiu
Publicado: (2026)

ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference
por: Li, Junjie, et al.
Publicado: (2026)

Hardware-Oriented Inference Complexity of Kolmogorov-Arnold Networks
por: Khalid, Bilal, et al.
Publicado: (2026)

Improving Pretraining Data Using Perplexity Correlations
por: Thrush, Tristan, et al.
Publicado: (2024)

OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions
por: Huang, Yu-Shin, et al.
Publicado: (2024)

Alzheimer's Dementia Detection Using Perplexity from Paired Large Language Models
por: Xiao, Yao, et al.
Publicado: (2025)

Rethinking GSPO: The Perplexity-Entropy Equivalence
por: Liu, Chi
Publicado: (2025)

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
por: Bu, Dake, et al.
Publicado: (2024)

Physics-informed time series analysis with Kolmogorov-Arnold Networks under Ehrenfest constraints
por: Sen, Abhijit, et al.
Publicado: (2025)

What is Wrong with Perplexity for Long-context Language Modeling?
por: Fang, Lizhe, et al.
Publicado: (2024)

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
por: Wang, Puyu, et al.
Publicado: (2026)

Predicting LLM Reasoning Performance with Small Proxy Model
por: Koh, Woosung, et al.
Publicado: (2025)

Implicit Steganography Beyond the Constraints of Modality
por: Song, Sojeong, et al.
Publicado: (2023)

Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography
por: Li, Songze, et al.
Publicado: (2025)

Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression
por: Kim, Kwangho, et al.
Publicado: (2026)

When Can Proxies Improve the Sample Complexity of Preference Learning?
por: Zhu, Yuchen, et al.
Publicado: (2024)

Non-Uniform Memory Sampling in Experience Replay
por: Krutsylo, Andrii
Publicado: (2025)

The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning
por: Goldblum, Micah, et al.
Publicado: (2023)

Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy
por: Zhang, Xiaoyun, et al.
Publicado: (2025)

Boosting Digital Safeguards: Blending Cryptography and Steganography
por: Maiti, Anamitra, et al.
Publicado: (2024)

Optimization, Generalization and Differential Privacy Bounds for Gradient Descent on Kolmogorov-Arnold Networks
por: Wang, Puyu, et al.
Publicado: (2026)

Reinforcement Learning Fine-Tunes a Sparse Subnetwork in Large Language Models
por: Balashov, Andrii
Publicado: (2025)

Granger Causality Detection with Kolmogorov-Arnold Networks
por: Lin, Hongyu, et al.
Publicado: (2024)

Proxy-Based Approximation of Shapley and Banzhaf Interactions
por: Thies, Santo M. A. R., et al.
Publicado: (2026)

Perplexity Cannot Always Tell Right from Wrong
por: Veličković, Petar, et al.
Publicado: (2026)