← Security & Privacy
Security & Privacy ›

Privacy

626 directly classified papers

Papers per year

Papers

Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging EMNLP 2025
Avoiding Copyright Infringement via Large Language Model Unlearning NAACL 2025
Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking CVPR 2025
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025
Role-Aware Language Models for Secure and Contextualized Access Control in Organizations IJCNLP 2025
From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models NAACL 2025
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks ACL 2025
Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In NAACL 2025
Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems IJCNLP 2025
Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models NAACL 2025
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework EMNLP 2025
Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems NAACL 2025
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization IJCNLP 2025
Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models CVPR 2025
Augmented Adversarial Trigger Learning NAACL 2025
Resource-Efficient Anonymization of Textual Data via Knowledge Distillation from Large Language Models COLING 2025
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents NAACL 2025
HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech NAACL 2025
RecordTwin: Towards Creating Safe Synthetic Clinical Corpora ACL 2025
TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025
CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications IJCNLP 2025
Named Entity Inference Attacks on Clinical LLMs: Exploring Privacy Risks and the Impact of Mitigation Strategies NAACL 2025
Defense Against Prompt Injection Attack by Leveraging Attack Techniques ACL 2025
Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts NAACL 2025
Privacy Preserving Solution of DCOPs by Local Search IJCAI 2025