Artificial Intelligence › Core AI ›

Privacy

490 directly classified papers

Papers per year

Papers

RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification ACL 2025

Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification NAACL 2025

Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting AAAI 2025

Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport ACL 2025

CDI: Copyrighted Data Identification in Diffusion Models CVPR 2025

Erasing Undesirable Influence in Diffusion Models CVPR 2025

Data-centric NLP Backdoor Defense from the Lens of Memorization NAACL 2025

Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation CVPR 2025

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning CVPR 2025

Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models CVPR 2025

SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models CVPR 2025

ACE: Anti-Editing Concept Erasure in Text-to-Image Models CVPR 2025

Black Hole-Driven Identity Absorbing in Diffusion Models CVPR 2025

TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025

Do Not DeepFake Me: Privacy-Preserving Neural 3D Head Reconstruction Without Sensitive Images AAAI 2025

PII-Scope: A Comprehensive Study on Training Data Privacy Leakage in Pretrained LLMs AACL 2025

Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes AAAI 2025

TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods NAACL 2025

Balancing Privacy and Utility in Personal LLM Writing Tasks: An Automated Pipeline for Evaluating Anonymizations NAACL 2025

SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025

Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025

Investigating User Perspectives on Differentially Private Text Privatization NAACL 2025

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection NAACL 2025

Lock on Target! Precision Unlearning via Directional Control EMNLP 2025

Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models CVPR 2025