{"total":58,"rows":[{"id":"2410.14273","title":"REEF: Representation Encoding Fingerprints for Large Language Models","created":"2024-10-18","cited_by_count":36,"area":null},{"id":"2508.11548","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","created":"2025-08-15","cited_by_count":20,"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":"2505.19864","title":"CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models","created":"2025-05-26","cited_by_count":17,"area":"rag"},{"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":"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":"2511.05797","title":"When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins","created":"2025-11-08","cited_by_count":9,"area":"safety"},{"id":"2504.02132","title":"One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image","created":"2025-04-02","cited_by_count":8,"area":"rag"},{"id":"2509.25448","title":"Fingerprinting LLMs via Prompt Injection","created":"2025-09-29","cited_by_count":8,"area":"safety"},{"id":"2509.26598","title":"Are Robust LLM Fingerprints Adversarially Robust?","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2511.14045","title":"Auditing Data Membership in Reinforcement Learning With Verifiable Rewards","created":"2025-11-18","cited_by_count":8,"area":null},{"id":"2603.01919","title":"Real Money, Fake Models: Deceptive Model Claims in Shadow APIs","created":"2026-03-02","cited_by_count":8,"area":null},{"id":"2411.05197","title":"Hardware and Software Platform Inference","created":"2024-11-07","cited_by_count":7,"area":null},{"id":"2607.10252","title":"One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions","created":"2026-07-11","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":"2508.20282","title":"Network-Level Prompt and Trait Leakage in Local Research Agents","created":"2025-08-27","cited_by_count":5,"area":"agents"},{"id":"2602.11083","title":"Token-Efficient Change Detection in LLM APIs","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2410.22725","title":"One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks","created":"2024-10-30","cited_by_count":4,"area":"diffusion"},{"id":"2501.16029","title":"FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting","created":"2025-01-27","cited_by_count":4,"area":null},{"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":"2510.06738","title":"AWM: Accurate Weight-Matrix Fingerprint for Large Language Models","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2601.14311","title":"Tracing the Data Trail: A Survey of Data Provenance, Transparency and Traceability in LLMs","created":"2026-01-19","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":"2605.29809","title":"Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing","created":"2026-05-28","cited_by_count":3,"area":"diffusion"},{"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":"2606.20470","title":"Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems","created":"2026-06-18","cited_by_count":2,"area":"agents"},{"id":"2608.26958","title":"Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable","created":"2026-08-27","cited_by_count":2,"area":"synth"},{"id":"2410.04454","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","created":"2024-10-06","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":"2601.11683","title":"Attesting Model Lineage by Consisted Knowledge Evolution with Fine-Tuning Trajectory","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2602.00772","title":"Provable Model Provenance Set for Large Language Models","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2605.15118","title":"Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.23175","title":"Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection","created":"2026-05-22","cited_by_count":1,"area":"safety"},{"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":"2605.29979","title":"Fingerprinting Inference Systems of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.02121","title":"Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"id":"2608.04626","title":"Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2609.31877","title":"A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2510.06525","title":"Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2601.09647","title":"Identifying Models Behind Text-to-Image Leaderboards","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2603.26328","title":"Verify Claimed Text-to-Image Models via Boundary-Aware Prompt Optimization","created":"2026-03-27","cited_by_count":0,"area":null},{"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":"2605.16035","title":"Who Owns This Agent? Tracing AI Agents Back to Their Owners","created":"2026-05-15","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":"2607.25227","title":"Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.25880","title":"Stemma: Induced Decision Regions Reveal LLM Provenance","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.02995","title":"SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels","created":"2026-08-04","cited_by_count":0,"area":"inference"},{"id":"2608.07786","title":"Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.16391","title":"Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.27954","title":"Not to Break, but to Attest: Adversarial Probes for Privacy-Preserving LLM Verification","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.00052","title":"AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.20614","title":"Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.33885","title":"Prospective Interpretation Risk: Principled Communication Control Between LLMs","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.38831","title":"Forging LLM Authorship Fingerprints with Targeted Rewriting","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00253","title":"System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2610.04169","title":"Language Model Fingerprinting Requires Rethinking Watermark Teachers","created":"2026-10-03","cited_by_count":0,"area":"safety"}],"next_cursor":null}