Copertina

Optimizing the Privacy-Utility Balance using Synthetic Data and Configurable Perturbation Pipelines

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sharma, Anantha, Devabhaktuni, Swetha, Mohan, Eklove
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning Probability
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

TableGuard -- Securing Structured & Unstructured Data
di: Sharma, Anantha, et al.
Pubblicazione: (2024)

Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
di: Yin, Yi, et al.
Pubblicazione: (2025)

PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning
di: Corbucci, Luca, et al.
Pubblicazione: (2024)

HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
di: Wang, Yuxin, et al.
Pubblicazione: (2024)

EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
di: Banayeeanzade, Amin, et al.
Pubblicazione: (2026)

Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version)
di: Abadi, Aydin, et al.
Pubblicazione: (2024)

PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)
di: Mancera, Gonzalo, et al.
Pubblicazione: (2025)

Toxicity Detection towards Adaptability to Changing Perturbations
di: Kang, Hankun, et al.
Pubblicazione: (2024)

BinaryShield: Cross-Service Threat Intelligence in LLM Services using Privacy-Preserving Fingerprints
di: Gill, Waris, et al.
Pubblicazione: (2025)

Position: Privacy Is Not Just Memorization!
di: Mireshghallah, Niloofar, et al.
Pubblicazione: (2025)

Probing the Robustness of Large Language Models Safety to Latent Perturbations
di: Gu, Tianle, et al.
Pubblicazione: (2025)

Learnable Privacy Neurons Localization in Language Models
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)

Trustworthy AI: Safety, Bias, and Privacy -- A Survey
di: Fang, Xingli, et al.
Pubblicazione: (2025)

Do Phone-Use Agents Respect Your Privacy?
di: Tang, Zhengyang, et al.
Pubblicazione: (2026)

PromptScreen: Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline
di: Rao, Akshaj Prashanth, et al.
Pubblicazione: (2025)

How Private is Your Attention? Bridging Privacy with In-Context Learning
di: Bonnerjee, Soham, et al.
Pubblicazione: (2025)

EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
di: Liao, Zeyi, et al.
Pubblicazione: (2024)

Preserving Privacy in Large Language Models: A Survey on Current Threats and Solutions
di: Miranda, Michele, et al.
Pubblicazione: (2024)

Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation
di: Li, Xianzhi, et al.
Pubblicazione: (2024)

The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
di: Chen, Xiaoyi, et al.
Pubblicazione: (2023)

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
di: Sarwar, Nobin, et al.
Pubblicazione: (2025)

DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models
di: Liu, Yanming, et al.
Pubblicazione: (2024)

DOMBA: Double Model Balancing for Access-Controlled Language Models via Minimum-Bounded Aggregation
di: Segal, Tom, et al.
Pubblicazione: (2024)

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models
di: Chu, Junjie, et al.
Pubblicazione: (2024)

MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification
di: Jiang, Weisen, et al.
Pubblicazione: (2026)

The DCR Delusion: Measuring the Privacy Risk of Synthetic Data
di: Yao, Zexi, et al.
Pubblicazione: (2025)

IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization
di: Frikha, Ahmed, et al.
Pubblicazione: (2024)

Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning
di: Li, Jianwei, et al.
Pubblicazione: (2023)

KIPPS: Knowledge infusion in Privacy Preserving Synthetic Data Generation
di: Kotal, Anantaa, et al.
Pubblicazione: (2024)

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
di: Zhang, Mohan, et al.
Pubblicazione: (2026)

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
di: Zhao, Andrew, et al.
Pubblicazione: (2025)

Are Normalizing Flows the Key to Unlocking the Exponential Mechanism?
di: Bridges, Robert A., et al.
Pubblicazione: (2023)

Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications
di: Liu, Shaobo, et al.
Pubblicazione: (2024)

What is in Your Safe Data? Identifying Benign Data that Breaks Safety
di: He, Luxi, et al.
Pubblicazione: (2024)

HexaCoder: Secure Code Generation via Oracle-Guided Synthetic Training Data
di: Hajipour, Hossein, et al.
Pubblicazione: (2024)

A Unified Learn-to-Distort-Data Framework for Privacy-Utility Trade-off in Trustworthy Federated Learning
di: Zhang, Xiaojin, et al.
Pubblicazione: (2024)

Generating Synthetic Health Sensor Data for Privacy-Preserving Wearable Stress Detection
di: Lange, Lucas, et al.
Pubblicazione: (2024)

Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
di: Shayegani, Erfan, et al.
Pubblicazione: (2025)

Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data
di: Baumgärtner, Tim, et al.
Pubblicazione: (2024)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
di: Wu, Xiaoyu, et al.
Pubblicazione: (2025)