{"total":68,"rows":[{"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":"2401.17256","title":"Weak-to-Strong Jailbreaking on Large Language Models","created":"2024-01-30","cited_by_count":107,"area":"safety"},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89,"area":"safety"},{"id":"2402.12329","title":"Query-Based Adversarial Prompt Generation","created":"2024-02-19","cited_by_count":62,"area":"alignment"},{"id":"2506.13759","title":"Discrete Diffusion in Large Language and Multimodal Models: A Survey","created":"2025-06-16","cited_by_count":61,"area":"mllm"},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50,"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":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30,"area":"safety"},{"id":"2404.06001","title":"Privacy Preserving Prompt Engineering: A Survey","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2502.01236","title":"Eliciting Language Model Behaviors with Investigator Agents","created":"2025-02-03","cited_by_count":23,"area":"agents"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2411.14033","title":"LLM-based Multi-Agent Systems: Techniques and Business Perspectives","created":"2024-11-21","cited_by_count":22,"area":"agents"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","cited_by_count":20,"area":"lr"},{"id":"2409.14729","title":"PROMPTFUZZ: Harnessing Fuzzing Techniques for Robust Testing of Prompt Injection in LLMs","created":"2024-09-23","cited_by_count":17,"area":"safety"},{"id":"2507.16372","title":"Depth Gives a False Sense of Privacy: LLM Internal States Inversion","created":"2025-07-22","cited_by_count":17,"area":null},{"id":"2408.02509","title":"Black-Box Adversarial Attacks on LLM-Based Code Completion","created":"2024-08-05","cited_by_count":14,"area":null},{"id":"2402.19200","title":"PRSA: Prompt Stealing Attacks against Real-World Prompt Services","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"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":"2504.07426","title":"Conditional Data Synthesis Augmentation","created":"2025-04-10","cited_by_count":8,"area":null},{"id":"2505.01177","title":"LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures","created":"2025-05-02","cited_by_count":8,"area":null},{"id":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","cited_by_count":7,"area":"safety"},{"id":"2507.04531","title":"DP-Fusion: Token-Level Differentially Private Inference for Large Language Models","created":"2025-07-06","cited_by_count":6,"area":"safety"},{"id":"2508.03703","title":"Privacy Risks of LLM-Empowered Recommender Systems: An Inversion Attack Perspective","created":"2025-07-20","cited_by_count":6,"area":null},{"id":"2509.14278","title":"Beyond Data Privacy: New Privacy Risks for Large Language Models","created":"2025-09-16","cited_by_count":6,"area":null},{"id":"2503.12896","title":"Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaboration","created":"2025-03-17","cited_by_count":5,"area":"rag"},{"id":"2510.12950","title":"An Investigation of Memorization Risk in Healthcare Foundation Models","created":"2025-10-14","cited_by_count":5,"area":null},{"id":"2504.21117","title":"Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts","created":"2025-04-29","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":"2509.21884","title":"You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors","created":"2025-09-26","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":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2501.07408","title":"Initial Findings on Sensor based Open Vocabulary Activity Recognition via Text Embedding Inversion","created":"2025-01-13","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":"2504.04373","title":"StyleRec: A Benchmark Dataset for Prompt Recovery in Writing Style Transformation","created":"2025-04-06","cited_by_count":2,"area":null},{"id":"2506.03355","title":"Robustness in Both Domains: CLIP Needs a Robust Text Encoder","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2507.01693","title":"GPT, But Backwards: Exactly Inverting Language Model Outputs","created":"2025-07-02","cited_by_count":2,"area":"safety"},{"id":"2507.04478","title":"Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2509.20909","title":"LogitTrace: Detecting Benchmark Contamination via Layerwise Logit Trajectories","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2609.10296","title":"The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding","created":"2026-09-09","cited_by_count":2,"area":null},{"id":"2502.07090","title":"Generative Distribution Prediction: A Unified Approach to Multimodal Learning","created":"2025-02-10","cited_by_count":1,"area":"diffusion"},{"id":"2505.12244","title":"Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2509.12652","title":"Don't Change My View: Ideological Bias Auditing in Large Language Models","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.10618","title":"Know Your Limits: Entropy Estimation Modeling for Compression and Generalization","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.13033","title":"Buy versus Build an LLM: A Decision Framework for Governments","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2607.26735","title":"Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives","created":"2026-07-29","cited_by_count":1,"area":"diffusion"},{"id":"2509.07936","title":"Feature Space Analysis by Guided Diffusion Model","created":"2025-09-09","cited_by_count":0,"area":"diffusion"},{"id":"2511.14808","title":"Transformer Injectivity & Geometric Robustness - Analytic Margins and Bi-Lipschitz Uniformity of Sequence-Level Hidden States","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2601.21543","title":"inversedMixup: Data Augmentation via Inverting Mixed Embeddings","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.11044","title":"Language Model Inversion through End-to-End Differentiation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.17566","title":"KA2L: A Knowledge-Aware Active Learning Framework for LLMs","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2603.20339","title":"Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs","created":"2026-03-20","cited_by_count":0,"area":"safety"},{"id":"2605.17314","title":"Weak-to-Strong Elicitation via Mismatched Wrong Drafts","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2605.22373","title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2605.27551","title":"On the Origin of Synthetic Information by Means of Steganographic Inheritance","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.28666","title":"Why Trust Your Agent? Empirical Security Gains from TRiSM-Guided Agentic Workflows in Healthcare","created":"2026-06-27","cited_by_count":0,"area":"agents"},{"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":"2607.10794","title":"Can Watermarking Techniques Help Prevent LLM Model Stealing?","created":"2026-07-12","cited_by_count":0,"area":"safety"},{"id":"2607.29378","title":"PTP: Previous-Token Prediction based LLM Inversion for Near-Exact Prompt Reconstruction","created":"2026-07-31","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":"2609.38149","title":"Pretraining Latent Information Feedback Transformers with Teacher Supervision","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.09920","title":"Inverting Multi-Vector Visual Document Indices","created":"2026-10-07","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}