{"total":98,"rows":[{"id":"2411.10541","title":"Does Prompt Formatting Have Any Impact on LLM Performance?","created":"2024-11-15","cited_by_count":141,"area":null},{"id":"2406.16838","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2407.15847","title":"LLMmap: Fingerprinting For Large Language Models","created":"2024-07-22","cited_by_count":58,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41,"area":null},{"id":"2403.09539","title":"Logits of API-Protected LLMs Leak Proprietary Information","created":"2024-03-14","cited_by_count":40,"area":null},{"id":"2504.04715","title":"Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs","created":"2025-04-07","cited_by_count":38,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2503.10633","title":"We Should Chart an Atlas of All the World's Models","created":"2025-03-13","cited_by_count":25,"area":null},{"id":"2504.13146","title":"Antidistillation Sampling","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2406.13843","title":"Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data","created":"2024-06-19","cited_by_count":20,"area":null},{"id":"2502.07776","title":"Auditing Prompt Caching in Language Model APIs","created":"2025-02-11","cited_by_count":20,"area":null},{"id":"2505.18893","title":"Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects","created":"2025-05-24","cited_by_count":19,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2408.02871","title":"Hide and Seek: Fingerprinting Large Language Models with Evolutionary Learning","created":"2024-08-06","cited_by_count":18,"area":null},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2405.13907","title":"Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries","created":"2024-05-22","cited_by_count":15,"area":null},{"id":"2406.04755","title":"LLM Whisperer: An Inconspicuous Attack to Bias LLM Responses","created":"2024-06-07","cited_by_count":15,"area":null},{"id":"2502.00706","title":"Model Provenance Testing for Large Language Models","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2508.19843","title":"SoK: Large Language Model Copyright Auditing via Fingerprinting","created":"2025-08-27","cited_by_count":15,"area":null},{"id":"2407.10886","title":"SLIP: Securing LLMs IP Using Weights Decomposition","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2406.04662","title":"Evaluating and Mitigating IP Infringement in Visual Generative AI","created":"2024-06-07","cited_by_count":13,"area":null},{"id":"2407.16607","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","created":"2024-07-23","cited_by_count":13,"area":null},{"id":"2505.17646","title":"Unveiling the Basin-Like Loss Landscape in Large Language Models","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2505.21627","title":"Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives","created":"2025-05-27","cited_by_count":13,"area":null},{"id":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2505.18471","title":"Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services","created":"2025-05-24","cited_by_count":10,"area":null},{"id":"2512.03816","title":"Log Probability Tracking of LLM APIs","created":"2025-12-03","cited_by_count":10,"area":null},{"id":"2411.07536","title":"Model Stealing for Any Low-Rank Language Model","created":"2024-11-12","cited_by_count":9,"area":null},{"id":"2506.17090","title":"Better Language Model Inversion by Compactly Representing Next-Token Distributions","created":"2025-06-20","cited_by_count":9,"area":null},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2410.11182","title":"A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality","created":"2024-10-15","cited_by_count":8,"area":null},{"id":"2502.11910","title":"Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2504.00147","title":"Universal Zero-shot Embedding Inversion","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2506.23706","title":"Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments","created":"2025-06-30","cited_by_count":8,"area":null},{"id":"2410.13569","title":"Learning on Model Weights using Tree Experts","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2503.16861","title":"In-House Evaluation Is Not Enough: Towards Robust Third-Party Flaw Disclosure for General-Purpose AI","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2606.22019","title":"Channel Location Constrains the Auditability of Subliminal Learning","created":"2026-06-20","cited_by_count":7,"area":null},{"id":"2407.02960","title":"ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets","created":"2024-07-03","cited_by_count":4,"area":null},{"id":"2503.01470","title":"Position: Ensuring mutual privacy is necessary for effective external evaluation of proprietary AI systems","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2506.15553","title":"Approximating Language Model Training Data from Weights","created":"2025-06-18","cited_by_count":4,"area":null},{"id":"2510.14086","title":"Every Language Model Has a Forgery-Resistant Signature","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2502.05325","title":"From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks","created":"2025-02-07","cited_by_count":3,"area":null},{"id":"2509.00973","title":"Clone What You Can't Steal: Black-Box LLM Replication via Logit Leakage and Distillation","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2512.09892","title":"Provably Learning from Modern Language Models via Low Logit Rank","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2606.05725","title":"An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic","created":"2026-06-04","cited_by_count":3,"area":null},{"id":"2606.15810","title":"Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2411.07691","title":"New Emerged Security and Privacy of Pre-trained Model: a Survey and Outlook","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2501.18669","title":"The Pitfalls of \"Security by Obscurity\" And What They Mean for Transparent AI","created":"2025-01-30","cited_by_count":2,"area":null},{"id":"2502.15902","title":"IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2504.06669","title":"NLP Security and Ethics, in the Wild","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2507.00724","title":"Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2602.00628","title":"From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.19844","title":"LLM-enabled Applications Require System-Level Threat Monitoring","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2605.04901","title":"On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference","created":"2026-05-06","cited_by_count":2,"area":null},{"id":"2608.03294","title":"Provably Learning Multi-Head Attention with Queries","created":"2026-08-04","cited_by_count":2,"area":null},{"id":"2408.02140","title":"VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2502.16701","title":"Beyond Release: Access Considerations for Generative AI Systems","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2511.19711","title":"CrypTorch: PyTorch-based Auto-tuning Compiler for Machine Learning with Multi-party Computation","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2512.17519","title":"Key-Conditioned Orthonormal Transform Gating (K-OTG): Multi-Key Access Control with Hidden-State Scrambling for LoRA-Tuned Models","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2601.16873","title":"Provably Learning Attention with Queries","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2605.18829","title":"Lossless Anti-Distillation Sampling","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.29979","title":"Fingerprinting Inference Systems of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2605.30040","title":"Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.06854","title":"The Geometry of Last-Layer Model Stealing","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.13892","title":"Crypto x AI, AI x Crypto: A Survey","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.25059","title":"What Does It Mean to Break a Distillation Defense?","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.28479","title":"Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2608.08195","title":"Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2408.02814","title":"Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services","created":"2024-08-05","cited_by_count":0,"area":null},{"id":"2410.23483","title":"Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2412.05842","title":"DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model","created":"2024-12-08","cited_by_count":0,"area":null},{"id":"2506.05867","title":"Stealix: Model Stealing via Prompt Evolution","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2506.22492","title":"Report on NSF Workshop on Science of Safe AI","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2507.19567","title":"Differentiating hype from practical applications of large language models in medicine -- a primer for healthcare professionals","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2508.11258","title":"Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2511.20312","title":"Data Augmentation Techniques to Reverse-Engineer Neural Network Weights from Input-Output Queries","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2512.01514","title":"Label Forensics: Interpreting Hard Labels in Black-Box Text Classifier","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2512.04580","title":"CryptoTensors: A Light-Weight Large Language Model File Format for Highly-Secure Model Distribution","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2602.18633","title":"DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2603.07460","title":"Where Do LLM-based Systems Break? A System-Level Security Framework for Risk Assessment and Treatment","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.27487","title":"Low Rank Adaptation for Adversarial Perturbation","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.23464","title":"Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.10091","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.27948","title":"RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31567","title":"FLARE-AI: Flaw Reporting for AI","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.01313","title":"Black-Box Inference of LLM Architectural Properties with Restrictive API Access","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.01023","title":"Caliber: Cross-Architecture Extraction-Cost Control for Score-Returning APIs","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.06631","title":"Cryptanalytic Extraction of Isolated Bias-Free GLU Feed-Forward Blocks by Antipodal Separation","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.26982","title":"JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.31142","title":"Auditing Anonymous AI Models: A Four-Stage Protocol for Black-Box Identity Verification","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.05125","title":"Evaluating and Recalibrating Probabilistic Classifiers from One-Bit Threshold Queries","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.25014","title":"Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2610.16790","title":"Logit Leakage through Floating-Point Bias Addition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}