Image de couverture de livre

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Panda, Ashwinee, Tang, Xinyu, Mahloujifar, Saeed, Sehwag, Vikash, Mittal, Prateek
Format:	Preprint
Publié:	2022
Sujets:	Machine Learning Artificial Intelligence Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Private Fine-tuning of Large Language Models with Zeroth-order Optimization
par: Tang, Xinyu, et autres
Publié: (2024)

Privacy Auditing of Large Language Models
par: Panda, Ashwinee, et autres
Publié: (2025)

Teach LLMs to Phish: Stealing Private Information from Language Models
par: Panda, Ashwinee, et autres
Publié: (2024)

Differentially Private Iterative Screening Rules for Linear Regression
par: Khanna, Amol, et autres
Publié: (2025)

Safety Alignment Should Be Made More Than Just a Few Tokens Deep
par: Qi, Xiangyu, et autres
Publié: (2024)

Differentially Private Worst-group Risk Minimization
par: Zhou, Xinyu, et autres
Publié: (2024)

Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists
par: Ly, Timothée, et autres
Publié: (2024)

Linearizing Models for Efficient yet Robust Private Inference
par: Sarkar, Sreetama, et autres
Publié: (2024)

Eclectic Rule Extraction for Explainability of Deep Neural Network based Intrusion Detection Systems
par: Ables, Jesse, et autres
Publié: (2024)

Impacts of Data Preprocessing and Hyperparameter Optimization on the Performance of Machine Learning Models Applied to Intrusion Detection Systems
par: Lima, Mateus Guimarães, et autres
Publié: (2024)

Auditing $f$-Differential Privacy in One Run
par: Mahloujifar, Saeed, et autres
Publié: (2024)

Improved Algorithms for Differentially Private Language Model Alignment
par: Chen, Keyu, et autres
Publié: (2025)

Attacking Byzantine Robust Aggregation in High Dimensions
par: Choudhary, Sarthak, et autres
Publié: (2023)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
par: Batra, Shourya, et autres
Publié: (2025)

Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
par: Wu, Ruihan, et autres
Publié: (2025)

SecAlign: Defending Against Prompt Injection with Preference Optimization
par: Chen, Sizhe, et autres
Publié: (2024)

Differentially Private Model Merging
par: Yin, Qichuan, et autres
Publié: (2026)

Challenges in Enabling Private Data Valuation
par: Fu, Yiwei, et autres
Publié: (2026)

Beyond Covariance Matrix: The Statistical Complexity of Private Linear Regression
par: Chen, Fan, et autres
Publié: (2025)

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization
par: Li, Xinyu, et autres
Publié: (2025)

Detecting Benchmark Contamination Through Watermarking
par: Sander, Tom, et autres
Publié: (2025)

Provable Privacy with Non-Private Pre-Processing
par: Hu, Yaxi, et autres
Publié: (2024)

Machine Learning with Privacy for Protected Attributes
par: Mahloujifar, Saeed, et autres
Publié: (2025)

Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
par: Jandali, Yaman, et autres
Publié: (2025)

Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddings
par: Sanchez, Ivan Montoya, et autres
Publié: (2025)

Differentially Private Deep Model-Based Reinforcement Learning
par: Rio, Alexandre, et autres
Publié: (2024)

Provable Differentially Private Computation of the Cross-Attention Mechanism
par: Ke, Yekun, et autres
Publié: (2024)

Differentially Private In-Context Learning with Nearest Neighbor Search
par: Koskela, Antti, et autres
Publié: (2025)

Evaluating Differentially Private Generation of Domain-Specific Text
par: Sun, Yidan, et autres
Publié: (2025)

AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning
par: Tang, Zehui, et autres
Publié: (2026)

Privacy Policy Enforcement Guardrails for Data-Sensitive Retrieval-Augmented Generation
par: Zafar, Osama, et autres
Publié: (2026)

GAVEL: Towards Rule-Based Safety Through Activation Monitoring
par: Rozenfeld, Shir, et autres
Publié: (2026)

Differentially Private Synthetic Data Release for Topics API Outputs
par: Dick, Travis, et autres
Publié: (2025)

Differentially Private Block-wise Gradient Shuffle for Deep Learning
par: Zagardo, David
Publié: (2024)

Privacy Assessment of Federated Learning using Private Personalized Layers
par: Jourdan, Théo, et autres
Publié: (2021)

Deep Efficient Private Neighbor Generation for Subgraph Federated Learning
par: Zhang, Ke, et autres
Publié: (2024)

Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing
par: Piran, Fardin Jalil, et autres
Publié: (2024)

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
par: Gao, Fengyu, et autres
Publié: (2024)

FERRET: Private Deep Learning Faster And Better Than DPSGD
par: Zagardo, David
Publié: (2025)

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
par: Pal, Soumyadeep, et autres
Publié: (2024)