Random

Follow this topic Ask about this topic

Recent momentum

-33%

8 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

3 new papers

A weekly snapshot of new work published in Random.

Period ending 2026-09-14

4 new papers

A weekly snapshot of new work published in Random.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Random.

122 papers

Latest in Random

Browse all topics →

Steganography Without Modification: Hidden Communication via LLM Seeds
Jun 8, 2026Felix Mächtle, Jonas Sander, Sebastian Berndt +3Steganography Large Language Model Watermarks
A machine-learning-assisted progressive digit-randomness screening framework for detecting non-random patterns in raw numerical research data
Jun 5, 2026Zhuphua CaoFalse Discovery Rate Random
Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models
Jun 4, 2026Huiyuan Zheng, Houtao Zhang, Boyang Wang +2Implicit Bias Random
Answer Presence Drives RAG Rewriting Gains
Jun 4, 2026Yuejie Li, Yueying Hua, Ke Yang +8Rewrite Reading
Can We Predict The Human Preference For Text-to-Image Content Prior To Generation And Is It Even Useful To Do So?
Jun 3, 2026Joong Ho Kim, Keith G. MillsText-To-Image Visual Generation
Sharp Low-Degree Thresholds for Planted-vs-Planted Testing
Jun 3, 2026Anda Skeja, Daniel Gutiérrez Espinoza, Fiona Skerman +1Two-Sample Testing Decision Thresholds
MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments
Jun 2, 2026Michael J. BommaritoMalware Detection Machine-Generated Text Detection
Constraint-Enhanced Physical Search through Correlation Matching
Jun 2, 2026Song-Ju KimEfficient Exploration Spatio-Temporal Correlations
Demystifying Pipeline Parallelism: First Theory for PipeDream
Jun 2, 2026Ivan Ilin, Peter RichtárikParallel Large Models
RRISE: Robust Radius Inference via a Surrogate Estimator
Jun 1, 2026Jong-Ik Park, Shreyas Chaudhari, Carlee Joe-Wong +1Smoothing Surrogate Performance
Linguistics-Aware Non-Distortionary LLM Watermarking
May 30, 2026Shinwoo Park, Hyejin Park, Hyeseon An +1Large Language Model Watermarks Random
The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
May 27, 2026Dueun Kim, Albert NoMasked Diffusion Language Models Training-Inference Mismatch
Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking
May 27, 2026Ziyang You, Huilong He, Xiaoke Yang +1Large Language Model Watermarks Language Model Evasion Attacks
Gumbel Machine: Counterfactual Student Writing Generation via Gumbel Noise Steering
May 26, 2026Hunter McNichols, Alexander Scarlatos, Mihai Dascalu +2Counterfactual Reasoning Random
CART Random Forests as Sequential Allocation over Random Opportunity Sets: A Stochastic-Control Theory of Ensemble Risk
May 26, 2026Tianxing Mei, Yingying Fan, Mingming Leng +1Random Forest Stochastic Optimal Control
F-RNG: Feed-Forward Relightable Neural Gaussians
May 25, 2026Guangming Fu, Jiahui Fan, Jian Yang +2Image Relighting Neural Rendering
Missing Pattern Recognized Diffusion Imputation Model for Missing Not At Random
May 25, 2026Gyuwon Sim, Sumin Lee, Heesun Bae +5Imputation Expectation-Maximization
Learning Treatment Effects during Resource Allocation via Priority-Queue Randomization
May 24, 2026JungHo Lee, Johnna Sundberg, Pim Welle +1Prioritization Bayesian Experimental Design
Automated Random Embedding for Practical Bayesian Optimization with Unknown Effective Dimension
May 22, 2026Hong Qian, Xiang Shu, Xiang Xia +5Bayesian Optimization Intrinsic Dimensionality
Worse than Random: The Importance of a Baseline for Unsupervised Feature Selection
May 21, 2026Muhammad Rajabinasab, Michael E. Houle, Oussama Chelly +1Feature Selection Unsupervised
FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data
May 21, 2026Maryam Moradpour, Jonas Harriehausen, Amirreza Aleyasin +3Random Forest Heterogeneity
Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
May 21, 2026Christian Janos Lebeda, David Erb, Tudor Cebere +1Differential Privacy Random Forest
Progressive Generalization Augmentation with Deeply Coupled RND-PPO and Domain-Prioritized Noise Injection for Robust Crop Management Reinforcement Learning
May 17, 2026Wu YangGaussian Noise Random
DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo
May 15, 2026Hanwen Wang, Weizhi Zhao, Xiangyu Wang +11Dexterous Manipulation Gripper
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
May 15, 2026Shuchan WangWatermarks Watermarking
The 99% Success Paradox: When Near-Perfect Retrieval Equals Random Selection
May 14, 2026Vyzantinos Repantis, Harshvardhan Singh, Tony Joseph +5Information Retrieval Metrics Selectivity
Provable Quantization with Randomized Hadamard Transform
May 13, 2026Ying Feng, Piotr Indyk, Michael Kapralov +2Calibration-Free Low-Bit Vector Quantization Quantization
DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
May 13, 2026Ziyang You, Liling Zheng, Xiaoke Yang +1Backdoor Attacks Random
Muon is Not That Special: Random or Inverted Spectra Work Just as Well
May 11, 2026Zakhar Shumaylov, Nathaël Da Costa, Peter Zaika +6Muon Optimizer Muon
Is Data Shapley Not Better than Random in Data Selection? Ask NASH
May 11, 2026Xiao Tian, Jue Fan, Rachael Hwee Ling Sim +3Shapley Value Random
Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching
May 10, 2026Kejia Ren, Gaotian Wang, Andrew S. Morgan +1Zero-Shot Sim-To-Real Transfer Robust Manipulation
Seed Hijacking of LLM Sampling and Quantum Random Number Defense
May 8, 2026Ziyang You, Xiaoke Yang, Zhanling Fan +3Language Model Evasion Attacks Random
Query-efficient model evaluation using cached responses
May 8, 2026Hayden Helm, Ben Johnson, Carey PriebeModel Evaluation Responses
Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
May 8, 2026Andy Dong, Ayfer ÖzgürDifferential Privacy Subsampling
Randomness is sometimes necessary for coordination
May 7, 2026Rohan Patil, Jai Malegaonkar, Henrik I. ChristensenCoordination Random
Estimate Level Adjustment For Inference With Proxies Under Random Distribution Shifts
May 7, 2026Steven Wilkins-Reeves, Alexandra N. M. Darmon, Deeksha SinhaConformal Inference Random
A Topological Sorting Criterion for Random Causal Directed Acyclic Graphs
May 7, 2026Alexander G. Reisach, Antoine Chambaz, Gilles Blanchard +1Causal Foundation Models Causal Reasoning
Constrained Contextual Bandits with Adversarial Contexts
May 7, 2026Dhruv Sarkar, Abhishek SinhaLinear Contextual Bandits Optimal Bandit Algorithms
S-LCG: Structured Linear Congruential Generator-Based Deterministic Algorithm for Search and Optimization
May 6, 2026Ahmed Qasim Mohammed, Haider Banka, Anamika SinghRandom Exploration-Exploitation Dilemma
Using Common Random Numbers for Simulation-based Planning with Rollouts
May 6, 2026Sandarbh Yadav, Frederic J Maliakkal, Harshad Khadilkar +1Rollout Random
Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks
May 5, 2026Diego MarcondesPartial Differential Equation Benchmarks Logarithmic Sobolev Inequalities
Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference
May 5, 2026Yi LiuLLM Inference Efficiency Retrieval Recall
On Surprising Effects of Risk-Aware Domain Randomization for Contact-Rich Sampling-based Predictive Control
May 5, 2026Sergio A. Esteban, Junheng Li, Vince Kurtz +1Model Predictive Control Random
Random-Effects Algorithm for Random Objects in Metric Spaces
May 4, 2026Marcos Matabuena, Mateo CámaraMetric Spaces Logistic Regression
Option-Order Randomisation Reveals a Distributional Position Attractor in Prompted Sandbagging
Apr 29, 2026Jon-Paul CacioliMmlu-Pro Distractor
Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
Apr 24, 2026Alberto Messina, Stefano ScottaRandom Perturbations
On Bayesian Softmax-Gated Mixture-of-Experts Models
Apr 22, 2026Nicola Bariletto, Huy Nguyen, Nhat Ho +1Mixture Models Bayesian
From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing
Apr 20, 2026Linfeng Liang, Xiao Cheng, Tsong Yueh Chen +1Scenario Generation Autonomous Driving
Improving reproducibility by controlling random seed stability in machine learning based estimation via bagging
Apr 20, 2026Nicholas Williams, Alejandro SchulerCross Validation Random
Learning Unanimously Acceptable Lotteries via Queries
Apr 19, 2026Davin Choo, Paul W. Goldberg, Nicholas TehLotteries Betting
GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models
Apr 15, 2026Yangyue Wang, Harshvardhan Sikka, Yash Mathur +3Graphical User Interface Spatial Reasoning
Assessing the Effect of Cross-Domain Mapping on Creativity in Humans and Large Language Models
Mar 19, 2026Qiawen Ella Liu, Marina Dubova, Henry Conklin +2Creativity Cognitive Science
Efficient privacy loss accounting for subsampling and random allocation
Feb 19, 2026Vitaly Feldman, Moshe ShenfeldDifferential Privacy Efficient Privacy Loss
Routing Absorption in Sparse Attention: Why Random Gates Are Hard to Beat
Feb 11, 2026Keston Aquino-MichaelsToken-Level Uncertainty Random
Spanning Tree Autoregressive Visual Generation
Nov 21, 2025Sangkyu Lee, Changho Lee, Janghoon Han +6Autoregressive Image Generation Visual Generation
RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator
Oct 1, 2025Kai Tang, Dipankar Bhattacharya, Hang Xu +3Fabric Robotic Arms
Gibbs randomness-compression proposition
May 29, 2025M. SüzenContext Compression Gibbs Measures
Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles
May 4, 2025Amir Ali Farzin, Yuen-Man Pun, Philipp Braun +1Convex Sets Zeroth-Order Optimization
Learning-based Adaptive Safety-Critical Control With Evolving Unsafe Regions
Mar 19, 2025Songqiao Hu, Zidong Wang, Zeyi Liu +2Control Barrier Functions Safety-Critical Scenarios
Evaluating Synthetic Data Generation for Domain Generalization in Fetal Brain MRI Segmentation
Nov 11, 2024Vladyslav Zalevskyi, Thomas Sanchez, Margaux Roulet +10Medical Image Generation Magnetic Resonance Imaging

Jun 8, 2026 · cs.CRJ/K move · Enter open · S save

Steganography Without Modification: Hidden Communication via LLM Seeds

Felix Mächtle, Jonas Sander, Sebastian Berndt, Ben Weimar+2

Institute for IT Security, University of Lübeck, Lübeck, Germany · Technische Hochschule Lübeck, Lübeck, Germany

We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits a structural property of deterministic decoding: pseudo-random number generators (PRNGs) used in inverse-transform sampling produce a seed-dependent sequence of token-level probability intervals that can be reconstructed from the generated text alone. A sender encodes a secret message in the PRNG seed before generation; a receiver reconstructs the intervals and recovers the seed, and thus the hidden payload, by exhaustive search over the seed space. We formalize two operational modes. In the known-prompt setting, sender and receiver share the prompt, enabling exact interval reconstruction and perfect seed recovery via forced alignment. In the unknown-prompt setting, only the generated text is available; approximate interval reconstruction combined with a maximum-hit-count scoring strategy still permits reliable recovery from sufficiently long outputs. Extensive experiments across six model families and five heterogeneous text domains show that, in the known-prompt setting, full 32-bit seed recovery from the complete 2^32 candidate space achieves up to 100% accuracy, depending on model and text domain, within 300 tokens and under 35 seconds on a single GPU. In the unknown-prompt setting, recovery reaches near-perfect accuracy at 600-800 tokens in about 12 seconds. We further analyze the influence of prompting strategies, tokenization ambiguities, and sampling hyperparameters on channel reliability. Moreover, we discuss several applications of our results: First, it allows for the steganographic transmission of 32 bits, but also shows that ignorance of the prompt is not a valid security assumption.

Steganography Large Language Model Watermarks Large Language Inference Engine Random Modifications

Open paper Ask about it PDF