Artificial Intelligence › Core AI ›

Privacy

490 directly classified papers

Papers per year

Papers

Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage EACL 2024

Disguise without Disruption: Utility-Preserving Face De-identification AAAI 2024

StegaStyleGAN: Towards Generic and Practical Generative Image Steganography AAAI 2024

Resource Efficient Deep Learning Hardware Watermarks with Signature Alignment AAAI 2024

Fostering Trustworthiness in Machine Learning Algorithms AAAI 2024

Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models ACL 2024

Improving Authorship Privacy: Adaptive Obfuscation with the Dynamic Selection of Techniques ACL 2024

GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysis ACL 2024

Exploring Memorization in Fine-tuned Language Models ACL 2024

Who Wrote this Code? Watermarking for Code Generation ACL 2024

GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick ACL 2024

Stealthy Attack on Large Language Model based Recommendation ACL 2024

Unlearning Traces the Influential Training Data of Language Models ACL 2024

Authorship Obfuscation in Multilingual Machine-Generated Text Detection EMNLP 2024

Private prediction for large-scale synthetic text generation EMNLP 2024

Can LLMs get help from other LLMs without revealing private information? ACL 2024

Protecting Privacy in Classifiers by Token Manipulation ACL 2024

TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification ACL 2024

Watermarking for Large Language Models ACL 2024

PostMark: A Robust Blackbox Watermark for Large Language Models EMNLP 2024

Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks (Student Abstract) AAAI 2023

Two-Stage Voice Anonymization for Enhanced Privacy INTERSPEECH 2023

Byzantine-Robust Learning on Heterogeneous Data via Gradient Splitting ICML 2023

Online Local Differential Private Quantile Inference via Self-normalization ICML 2023

Algorithms for bounding contribution for histogram estimation under user-level privacy ICML 2023