{"total":159,"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":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102,"area":"rag"},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2503.15547","title":"Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents","created":"2025-03-17","cited_by_count":87,"area":"agents"},{"id":"2411.09523","title":"Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents","created":"2024-11-14","cited_by_count":65,"area":"agents"},{"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":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"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":"2505.04806","title":"Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs","created":"2025-05-07","cited_by_count":34,"area":"safety"},{"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":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2410.23743","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","created":"2024-10-31","cited_by_count":29,"area":"lr"},{"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":"2405.20777","title":"Black-Box Detection of Language Model Watermarks","created":"2024-05-28","cited_by_count":23,"area":"safety"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2408.04870","title":"ConfusedPilot: Confused Deputy Risks in RAG-based LLMs","created":"2024-08-09","cited_by_count":22,"area":"rag"},{"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":"2412.20953","title":"GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search","created":"2024-12-30","cited_by_count":20,"area":"rag"},{"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":"2410.10811","title":"Deep Linear Probe Generators for Weight Space Learning","created":"2024-10-14","cited_by_count":17,"area":"mechinterp"},{"id":"2501.09798","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","created":"2025-01-16","cited_by_count":17,"area":"safety"},{"id":"2410.02099","title":"A Watermark for Black-Box Language Models","created":"2024-10-02","cited_by_count":16,"area":"safety"},{"id":"2506.11444","title":"GaussMarker: Robust Dual-Domain Watermark for Diffusion Models","created":"2025-06-13","cited_by_count":16,"area":"diffusion"},{"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":"2412.05734","title":"LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage","created":"2024-12-07","cited_by_count":13,"area":"agents"},{"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":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"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":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"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":"2508.01365","title":"ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models","created":"2025-08-02","cited_by_count":9,"area":"safety"},{"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":"2410.13274","title":"Breaking Chains: Unraveling the Links in Multi-Hop Knowledge Unlearning","created":"2024-10-17","cited_by_count":8,"area":"safety"},{"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":"2505.12442","title":"IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems","created":"2025-05-18","cited_by_count":8,"area":"agents"},{"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":"2509.25448","title":"Fingerprinting LLMs via Prompt Injection","created":"2025-09-29","cited_by_count":8,"area":"safety"},{"id":"2602.08401","title":"On Protecting Agentic Systems' Intellectual Property via Watermarking","created":"2026-02-09","cited_by_count":8,"area":"agents"},{"id":"2408.05061","title":"A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares","created":"2024-08-09","cited_by_count":7,"area":"safety"},{"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":"2412.07192","title":"PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips","created":"2024-12-10","cited_by_count":5,"area":"alignment"},{"id":"2502.13361","title":"RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answering","created":"2025-02-19","cited_by_count":5,"area":"rag"},{"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":"2507.11128","title":"What Should LLMs Forget? Quantifying Personal Data in LLMs for Right-to-Be-Forgotten Requests","created":"2025-07-15","cited_by_count":4,"area":"safety"},{"id":"2510.14086","title":"Every Language Model Has a Forgery-Resistant Signature","created":"2025-10-15","cited_by_count":4,"area":null},{"id":"2406.11039","title":"Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment","created":"2024-06-16","cited_by_count":3,"area":"alignment"},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"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":"2601.15678","title":"Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems","created":"2026-01-22","cited_by_count":3,"area":"rag"},{"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":"2506.05594","title":"SoK: Are Watermarks in LLMs Ready for Deployment?","created":"2025-06-05","cited_by_count":2,"area":"safety"},{"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":"2507.02850","title":"LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users","created":"2025-07-03","cited_by_count":2,"area":"alignment"},{"id":"2512.23132","title":"Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems","created":"2025-12-29","cited_by_count":2,"area":"agents"},{"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":"2608.04192","title":"Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills","created":"2026-08-04","cited_by_count":2,"area":"agents"},{"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":"2507.01752","title":"Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training","created":"2025-07-02","cited_by_count":1,"area":"safety"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"}],"next_cursor":"100"}