← Core AI
Artificial Intelligence › Core AI ›

Privacy

490 directly classified papers

Papers per year

Papers

WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off NIPS 2024
Beyond Slow Signs in High-fidelity Model Extraction NIPS 2024
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature NIPS 2024
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes NIPS 2024
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs NIPS 2024
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement NIPS 2024
$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning NIPS 2024
Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference NIPS 2024
Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection NIPS 2024
PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining NIPS 2024
United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories NIPS 2024
Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack NIPS 2024
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NIPS 2024
Auditing Privacy Mechanisms via Label Inference Attacks NIPS 2024
DAGER: Exact Gradient Inversion for Large Language Models NIPS 2024
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks NIPS 2024
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action NIPS 2024
Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models EMNLP 2024
The Limits of Differential Privacy in Online Learning NIPS 2024
Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation EMNLP 2024
DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models EMNLP 2024
Privacy Evaluation Benchmarks for NLP Models EMNLP 2024
Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares Extended Abstract COLT 2024
On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective COLT 2024
Data-mining and Extraction: the gold rush of AI on Indigenous Languages EACL 2024