{"total":68,"rows":[{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254,"area":null},{"id":"2407.10887","title":"Hey, That's My Model! Introducing Chain & Hash, An LLM Fingerprinting Technique","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"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":"2404.05188","title":"Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging","created":"2024-04-08","cited_by_count":19,"area":"safety"},{"id":"2503.04636","title":"Mark Your LLM: Detecting the Misuse of Open-Source Large Language Models via Watermarking","created":"2025-03-06","cited_by_count":19,"area":"safety"},{"id":"2506.06975","title":"Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test","created":"2025-06-08","cited_by_count":18,"area":null},{"id":"2405.02466","title":"ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Models","created":"2024-05-03","cited_by_count":16,"area":null},{"id":"2409.19993","title":"Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges","created":"2024-09-30","cited_by_count":15,"area":"safety"},{"id":"2502.00706","title":"Model Provenance Testing for Large Language Models","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2505.19504","title":"DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation","created":"2025-05-26","cited_by_count":14,"area":"distill"},{"id":"2506.01631","title":"Gradient-Based Model Fingerprinting for LLM Similarity Detection and Family Classification","created":"2025-06-02","cited_by_count":14,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2510.19796","title":"Blackbox Model Provenance via Palimpsestic Membership Inference","created":"2025-10-22","cited_by_count":11,"area":"safety"},{"id":"2407.03160","title":"SOS! Soft Prompt Attack Against Open-Source Large Language Models","created":"2024-07-03","cited_by_count":10,"area":"safety"},{"id":"2502.12292","title":"Independence Tests for Language Models","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2509.26404","title":"SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From","created":"2025-09-30","cited_by_count":10,"area":null},{"id":"2505.16723","title":"LLM Fingerprinting via Semantically Conditioned Watermarks","created":"2025-05-22","cited_by_count":9,"area":"safety"},{"id":"2411.05091","title":"Watermarking Language Models through Language Models","created":"2024-11-07","cited_by_count":8,"area":"safety"},{"id":"2506.22802","title":"Riemannian-Geometric Fingerprints of Generative Models","created":"2025-06-28","cited_by_count":8,"area":null},{"id":"2509.26598","title":"Are Robust LLM Fingerprints Adversarially Robust?","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2602.08401","title":"On Protecting Agentic Systems' Intellectual Property via Watermarking","created":"2026-02-09","cited_by_count":8,"area":"agents"},{"id":"2502.20589","title":"LLMs Have Rhythm: Fingerprinting Large Language Models Using Inter-Token Times and Network Traffic Analysis","created":"2025-02-27","cited_by_count":7,"area":null},{"id":"2503.21805","title":"ImF: Implicit Fingerprint for Large Language Models","created":"2025-03-25","cited_by_count":7,"area":null},{"id":"2505.16785","title":"CoTSRF: Utilize Chain of Thought as Stealthy and Robust Fingerprint of Large Language Models","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2510.18333","title":"Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption","created":"2025-10-21","cited_by_count":7,"area":"safety"},{"id":"2410.22307","title":"SVIP: Towards Verifiable Inference of Open-source Large Language Models","created":"2024-10-29","cited_by_count":6,"area":null},{"id":"2501.18712","title":"Invisible Traces: Using Hybrid Fingerprinting to identify underlying LLMs in GenAI Apps","created":"2025-01-30","cited_by_count":5,"area":null},{"id":"2503.04332","title":"The Challenge of Identifying the Origin of Black-Box Large Language Models","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2602.03396","title":"Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2605.11036","title":"Sequential Behavioral Watermarking for LLM Agents","created":"2026-05-11","cited_by_count":5,"area":"agents"},{"id":"2504.01032","title":"Who Owns the Output? Bridging Law and Technology in LLMs Attribution","created":"2025-03-29","cited_by_count":4,"area":null},{"id":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2510.16367","title":"EditMark: Watermarking Large Language Models based on Model Editing","created":"2025-10-18","cited_by_count":4,"area":"safety"},{"id":"2508.02092","title":"FPEdit: Robust LLM Fingerprinting through Localized Parameter Editing","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2509.03117","title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","created":"2025-09-03","cited_by_count":3,"area":"safety"},{"id":"2510.06738","title":"AWM: Accurate Weight-Matrix Fingerprint for Large Language Models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2605.29524","title":"KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2406.02481","title":"Large Language Models as Carriers of Hidden Messages","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2410.19096","title":"Watermarking Large Language Models and the Generated Content: Opportunities and Challenges","created":"2024-10-24","cited_by_count":2,"area":"safety"},{"id":"2505.01007","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","created":"2025-05-02","cited_by_count":2,"area":null},{"id":"2512.03620","title":"SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2605.06458","title":"Invariant Features in Language Models: Geometric Characterization and Model Attribution","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.16462","title":"Asking Back: Interaction-Layer Antidistillation Watermarks","created":"2026-05-15","cited_by_count":2,"area":"distill"},{"id":"2605.28890","title":"Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2508.06309","title":"Matrix-Driven Identification and Reconstruction of LLM Weight Homology","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2508.09021","title":"Attacks and Defenses Against LLM Fingerprinting","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2510.04966","title":"ActiveMark: on watermarking of visual foundation models via massive activations","created":"2025-10-06","cited_by_count":1,"area":"safety"},{"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":"2601.08189","title":"ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models","created":"2026-01-13","cited_by_count":1,"area":"safety"},{"id":"2602.04894","title":"Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.18845","title":"Echoes of ownership: Adversarial-guided dual injection for copyright protection in MLLMs","created":"2026-02-21","cited_by_count":1,"area":null},{"id":"2604.21083","title":"Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.29245","title":"Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content","created":"2026-05-28","cited_by_count":1,"area":"safety"},{"id":"2608.08195","title":"Targeted Counterfactual Fingerprinting for Black-Box LLM Ownership Verification","created":"2026-08-08","cited_by_count":1,"area":null},{"id":"2601.08223","title":"DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection","created":"2026-01-13","cited_by_count":0,"area":"safety"},{"id":"2601.22692","title":"FNF: Functional Network Fingerprint for Large Language Models","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.15220","title":"InterPol: De-anonymizing LM Arena via Interpolated Preference Learning","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.18793","title":"Functional Subspace Watermarking for Large Language Models","created":"2026-03-19","cited_by_count":0,"area":"safety"},{"id":"2604.18179","title":"Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs","created":"2026-04-20","cited_by_count":0,"area":"mechinterp"},{"id":"2605.28597","title":"Position: Retire the \"Positive Backdoor\" Label -- Secret Alignment Requires Strict and Systematic Evaluation","created":"2026-05-27","cited_by_count":0,"area":"alignment"},{"id":"2606.17123","title":"LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains","created":"2026-06-15","cited_by_count":0,"area":"safety"},{"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":"2607.20440","title":"Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2609.32749","title":"Retrospective Distillation Attribution via Normalized Response Similarity","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.04169","title":"Language Model Fingerprinting Requires Rethinking Watermark Teachers","created":"2026-10-03","cited_by_count":0,"area":"safety"},{"id":"2610.15685","title":"Radioactive Feedback: Tracing Models Trained by Label-Only LLM Supervision","created":"2026-10-11","cited_by_count":0,"area":"distill"}],"next_cursor":null}