{"total":70,"rows":[{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375,"area":"safety"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2410.05451","title":"SecAlign: Defending Against Prompt Injection with Preference Optimization","created":"2024-10-07","cited_by_count":210,"area":"alignment"},{"id":"2305.17359","title":"DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text","created":"2023-05-27","cited_by_count":129,"area":null},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2312.17673","title":"Jatmo: Prompt Injection Defense by Task-Specific Finetuning","created":"2023-12-29","cited_by_count":106,"area":"safety"},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"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":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2403.04801","title":"Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs","created":"2024-03-05","cited_by_count":33,"area":"agents"},{"id":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30,"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":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2311.02240","title":"Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems","created":"2023-11-03","cited_by_count":28,"area":"safety"},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2402.14845","title":"Purifying Large Language Models by Ensembling a Small Language Model","created":"2024-02-19","cited_by_count":25,"area":"safety"},{"id":"2406.10952","title":"Avoiding Copyright Infringement via Large Language Model Unlearning","created":"2024-06-16","cited_by_count":24,"area":"safety"},{"id":"2407.02943","title":"PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding","created":"2024-07-03","cited_by_count":24,"area":null},{"id":"2508.13152","title":"RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns","created":"2025-08-18","cited_by_count":24,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2404.11262","title":"Sampling-based Pseudo-Likelihood for Membership Inference Attacks","created":"2024-04-17","cited_by_count":20,"area":"safety"},{"id":"2410.08190","title":"Poison-splat: Computation Cost Attack on 3D Gaussian Splatting","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2310.02469","title":"PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2309.17319","title":"Building Privacy-Preserving and Secure Geospatial Artificial Intelligence Foundation Models","created":"2023-09-29","cited_by_count":12,"area":null},{"id":"2405.17423","title":"Privacy-Aware Visual Language Models","created":"2024-05-27","cited_by_count":12,"area":"mllm"},{"id":"2505.10212","title":"Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M","created":"2025-05-15","cited_by_count":12,"area":null},{"id":"2403.08481","title":"SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks","created":"2024-03-13","cited_by_count":11,"area":"safety"},{"id":"2502.12658","title":"R.R.: Unveiling LLM Training Privacy through Recollection and Ranking","created":"2025-02-18","cited_by_count":10,"area":"safety"},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2507.05578","title":"The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation","created":"2025-07-08","cited_by_count":10,"area":"safety"},{"id":"2407.02596","title":"Towards More Realistic Extraction Attacks: An Adversarial Perspective","created":"2024-07-02","cited_by_count":8,"area":null},{"id":"2503.06040","title":"Mitigating Memorization in LLMs using Activation Steering","created":"2025-03-08","cited_by_count":8,"area":"mechinterp"},{"id":"2409.14747","title":"Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting","created":"2024-09-23","cited_by_count":7,"area":"safety"},{"id":"2506.19399","title":"Automated Detection of Pre-training Text in Black-box LLMs","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2507.03367","title":"Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2409.12020","title":"Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorization","created":"2024-09-18","cited_by_count":4,"area":null},{"id":"2601.18110","title":"AttenMIA: LLM Membership Inference Attack through Attention Signals","created":"2026-01-26","cited_by_count":4,"area":"safety"},{"id":"2605.23158","title":"What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference","created":"2026-05-22","cited_by_count":4,"area":null},{"id":"2412.19496","title":"Multi-PA: A Multi-perspective Benchmark on Privacy Assessment for Large Vision-Language Models","created":"2024-12-27","cited_by_count":3,"area":"mllm"},{"id":"2404.17143","title":"Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper","created":"2024-04-26","cited_by_count":2,"area":null},{"id":"2412.20087","title":"On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs","created":"2024-12-28","cited_by_count":2,"area":null},{"id":"2510.07452","title":"PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2602.18733","title":"A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2410.18824","title":"PSY: Posterior Sampling Based Privacy Enhancer in Large Language Models","created":"2024-10-24","cited_by_count":1,"area":"safety"},{"id":"2411.07070","title":"On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2506.06060","title":"Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2507.04771","title":"Efficient Unlearning with Privacy Guarantees","created":"2025-07-07","cited_by_count":1,"area":"safety"},{"id":"2508.02573","title":"Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2509.15861","title":"ToFU: Transforming How Federated Learning Systems Forget User Data","created":"2025-09-19","cited_by_count":1,"area":"safety"},{"id":"2510.20612","title":"Black Box Absorption: LLMs Undermining Innovative Ideas","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2602.20461","title":"Nonparametric Teaching of Attention Learners","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2603.18235","title":"Toward Reliable, Safe, and Secure LLMs for Scientific Applications","created":"2026-03-18","cited_by_count":1,"area":"agents"},{"id":"2604.18697","title":"Beyond Indistinguishability: Measuring Extraction Risk in LLM APIs","created":"2026-04-20","cited_by_count":1,"area":"safety"},{"id":"2606.17110","title":"Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2609.30935","title":"Estimating and Orthogonalizing Unknown Pre-training Gradients for Continual Fine-tuning of Large Language Models","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2403.18205","title":"Exploring the Privacy Protection Capabilities of Chinese Large Language Models","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2505.06284","title":"DMRL: Data- and Model-aware Reward Learning for Data Extraction","created":"2025-05-07","cited_by_count":0,"area":"alignment"},{"id":"2505.13819","title":"Fragments to Facts: Partial-Information Fragment Inference from LLMs","created":"2025-05-20","cited_by_count":0,"area":"safety"},{"id":"2510.10902","title":"Auditing Information Disclosure During Large-Scale Gradient-Based Training via Gradient Uniqueness","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2512.12914","title":"CTIGuardian: A Few-Shot Framework for Mitigating Privacy Leakage in Fine-Tuned LLMs","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2512.13352","title":"On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2603.01550","title":"Extracting Training Dialogue Data from Large Language Model based Task Bots","created":"2026-03-02","cited_by_count":0,"area":"safety"},{"id":"2603.12598","title":"Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating","created":"2026-03-13","cited_by_count":0,"area":"mllm"},{"id":"2605.05224","title":"Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.22373","title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2605.24173","title":"Extracting Training Data from Diffusion Language Models via Infilling","created":"2026-05-22","cited_by_count":0,"area":"diffusion"},{"id":"2607.22489","title":"\\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating","created":"2026-07-24","cited_by_count":0,"area":null}],"next_cursor":null}