conftrace_
← Security & Privacy
Security & Privacy ›

Privacy

638 papers

Papers per year

1
30
203
'15
'20
'25

Papers

AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO EMNLP 2025
Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025
SUA: Stealthy Multimodal Large Language Model Unlearning Attack EMNLP 2025
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025
Membership and Memorization in LLM Knowledge Distillation EMNLP 2025
Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation EMNLP 2025
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study EMNLP 2025
VLA-Mark: A cross modal watermark for large vision-language alignment models EMNLP 2025
TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent EMNLP 2025
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing EMNLP 2025
Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss EMNLP 2025
Controlled Generation for Private Synthetic Text EMNLP 2025
Personalized Language Models via Privacy-Preserving Evolutionary Model Merging EMNLP 2025
Retracing the Past: LLMs Emit Training Data When They Get Lost EMNLP 2025
Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization EMNLP 2025
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage EMNLP 2025
Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations EMNLP 2025
Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents EMNLP 2025
Tracing Training Footprints: A Calibration Approach for Membership Inference Attacks Against Multimodal Large Language Models EMNLP 2025
Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images! ICCV 2025
Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack ICCV 2025
Membership Inference Attacks with False Discovery Rate Control ICCV 2025
StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025
Backdooring Self-Supervised Contrastive Learning by Noisy Alignment ICCV 2025
Backdoor Mitigation by Distance-Driven Detoxification ICCV 2025