56 lines (56 loc) · 11.5 KB

C0. General

[2026/02] AgentLeak: A Full-Stack Benchmark for Privacy Leakage in Multi-Agent LLM Systems
[2025/11] MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
[2025/10] Autonomy Matters: A Study on Personalization-Privacy Dilemma in LLM Agents
[2025/09] Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models
[2025/09] Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
[2025/09] Beyond Data Privacy: New Privacy Risks for Large Language Models
[2025/09] User Privacy and Large Language Models: An Analysis of Frontier Developers' Privacy Policies
[2025/08] Searching for Privacy Risks in LLM Agents via Simulation
[2025/08] Adaptive Backtracking for Privacy Protection in Large Language Models
[2025/08] PRvL: Quantifying the Capabilities and Risks of Large Language Models for PII Redaction
[2025/07] Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation
[2025/07] Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training
[2025/06] PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty
[2025/06] Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
[2025/06] SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
[2025/06] Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
[2025/06] Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
[2025/05] When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs
[2025/05] TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent
[2025/05] Can Large Language Models Really Recognize Your Name?
[2025/05] Automated Profile Inference with Language Model Agents
[2025/05] A Survey on Privacy Risks and Protection in Large Language Models
[2025/04] Doxing via the Lens: Revealing Privacy Leakage in Image Geolocation for Agentic Multi-Modal Large Reasoning Model
[2025/03] AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
[2025/02] The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text
[2025/02] A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation
[2025/02] Unveiling Privacy Risks in LLM Agent Memory
[2025/02] Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
[2024/12] PrivAgent: Agentic-based Red-teaming for LLM Privacy Leakage
[2024/12] VLSBench: Unveiling Visual Leakage in Multimodal Safety
[2024/11] Can Humans Oversee Agents to Prevent Privacy Leakage? A Study on Privacy Awareness, Preferences, and Trust in Language Model Agents
[2024/10] Empowering Users in Digital Privacy Management through Interactive LLM-Based Agents
[2024/08] LLM-PBE: Assessing Data Privacy in Large Language Models
[2024/08] Data Exposure from LLM Apps: An In-depth Investigation of OpenAI's GPTs
[2024/08] Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching
[2024/08] Reducing Privacy Risks in Online Self-Disclosures with Language Models
[2024/08] Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
[2024/06] Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
[2024/05] Learnable Privacy Neurons Localization in Language Models
[2024/05] Information Leakage from Embedding in Large Language Models
[2024/05] Air Gap: Protecting Privacy-Conscious Conversational Agents
[2024/04] Can LLMs get help from other LLMs without revealing private information?
[2024/03] Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
[2024/03] PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps
[2024/03] Visual Privacy Auditing with Diffusion Models
[2024/03] Analysis of Privacy Leakage in Federated Large Language Models
[2024/03] CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
[2024/02] The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
[2024/01] Excuse me, sir? Your language model is leaking (information)
[2023/10] Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning
[2023/09] Beyond Memorization: Violating Privacy via Inference with Large Language Models
[2023/09] Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
[2023/09] Privacy Side Channels in Machine Learning Systems
[2023/07] ProPILE: Probing Privacy Leakage in Large Language Models
[2023/05] ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review