← Security & Privacy
Security & Privacy ›

Privacy

626 directly classified papers

Papers per year

Papers

Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026
SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning WACV 2026
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refine NAACL 2025
Augmented Adversarial Trigger Learning NAACL 2025
Named Entity Inference Attacks on Clinical LLMs: Exploring Privacy Risks and the Impact of Mitigation Strategies NAACL 2025
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025
Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In NAACL 2025
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025
Jailbreaking with Universal Multi-Prompts NAACL 2025
Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems NAACL 2025
HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech NAACL 2025
TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025
Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts NAACL 2025
Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining NAACL 2025
MYOPIA: Protecting Face Privacy from Malicious Personalized Text-to-Image Synthesis via Unlearnable Examples AAAI 2025
Avoiding Copyright Infringement via Large Language Model Unlearning NAACL 2025
Vulnerability of Large Language Models to Output Prefix Jailbreaks: Impact of Positions on Safety NAACL 2025
From Intentions to Techniques: A Comprehensive Taxonomy and Challenges in Text Watermarking for Large Language Models NAACL 2025
Role-Aware Language Models for Secure and Contextualized Access Control in Organizations IJCNLP 2025
Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems IJCNLP 2025
IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization IJCNLP 2025
Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data IJCNLP 2025
CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications IJCNLP 2025
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025
Dynamic Guided and Domain Applicable Safeguards for Enhanced Security in Large Language Models NAACL 2025