Copertina

Inducing Uncertainty on Open-Weight Models for Test-Time Privacy in Image Recognition

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ashiq, Muhammad H., Triantafillou, Peter, Tseng, Hung Yun, Chrysos, Grigoris G.
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy
di: Kaiser, Johannes, et al.
Pubblicazione: (2026)

Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
di: Wei, Boyi, et al.
Pubblicazione: (2025)

On Evaluating the Durability of Safeguards for Open-Weight LLMs
di: Qi, Xiangyu, et al.
Pubblicazione: (2024)

Privacy and Security Threat for OpenAI GPTs
di: Wenying, Wei, et al.
Pubblicazione: (2025)

Connect the dots: Dataset Condensation, Differential Privacy, and Adversarial Uncertainty
di: Odoh, Kenneth
Pubblicazione: (2024)

Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models
di: Chen, Linzhi, et al.
Pubblicazione: (2025)

NOIR: Privacy-Preserving Generation of Code with Open-Source LLMs
di: Nguyen, Khoa, et al.
Pubblicazione: (2026)

Privacy in Responsible AI: Approaches to Facial Recognition from Cloud Providers
di: Elivanova, Anna
Pubblicazione: (2025)

Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization
di: Lin, Zhixin, et al.
Pubblicazione: (2026)

PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
di: Zeng, Ziqian, et al.
Pubblicazione: (2024)

CanaryBench: Stress Testing Privacy Leakage in Cluster-Level Conversation Summaries
di: Mehta, Deep
Pubblicazione: (2026)

Stealing AI Model Weights Through Covert Communication Channels
di: Barbaza, Valentin, et al.
Pubblicazione: (2025)

On the Privacy of LLMs: An Ablation Study
di: Makhlouf, Karima, et al.
Pubblicazione: (2026)

Efficient local linearity regularization to overcome catastrophic overfitting
di: Rocamora, Elias Abad, et al.
Pubblicazione: (2024)

PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing
di: Tamboli, Dipesh, et al.
Pubblicazione: (2026)

User Behavior Analysis in Privacy Protection with Large Language Models: A Study on Privacy Preferences with Limited Data
di: Yang, Haowei, et al.
Pubblicazione: (2025)

Tabular Data Synthesis with Differential Privacy: A Survey
di: Yang, Mengmeng, et al.
Pubblicazione: (2024)

Privacy-Preserving Diffusion Model Using Homomorphic Encryption
di: Chen, Yaojian, et al.
Pubblicazione: (2024)

SoK: Semantic Privacy in Large Language Models
di: Ma, Baihe, et al.
Pubblicazione: (2025)

Parallel Test-Time Scaling with Multi-Sequence Verifiers
di: Kim, Yegon, et al.
Pubblicazione: (2026)

Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
di: Fang, Xingli, et al.
Pubblicazione: (2026)

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
di: Hossain, Saad, et al.
Pubblicazione: (2026)

Towards Provable (In)Secure Model Weight Release Schemes
di: Yang, Xin, et al.
Pubblicazione: (2025)

LLM-PBE: Assessing Data Privacy in Large Language Models
di: Li, Qinbin, et al.
Pubblicazione: (2024)

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
di: Arzanipour, Atousa, et al.
Pubblicazione: (2025)

Mapping Smarter, Not Harder: A Test-Time Reinforcement Learning Agent That Improves Without Labels or Model Updates
di: Tsao, Wen-Kwang, et al.
Pubblicazione: (2025)

Robust Privacy: Inference-Time Privacy through Certified Robustness
di: Jin, Jiankai, et al.
Pubblicazione: (2026)

Invariant-based Robust Weights Watermark for Large Language Models
di: Guo, Qingxiao, et al.
Pubblicazione: (2025)

Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
di: Dang, Hung
Pubblicazione: (2026)

Federated Split Learning for Human Activity Recognition with Differential Privacy
di: Ndeko, Josue, et al.
Pubblicazione: (2024)

MAGNETO: Edge AI for Human Activity Recognition -- Privacy and Personalization
di: Zuo, Jingwei, et al.
Pubblicazione: (2024)

A Survey: Towards Privacy and Security in Mobile Large Language Models
di: Xu, Honghui, et al.
Pubblicazione: (2025)

On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction
di: Ezzeddine, Fatima, et al.
Pubblicazione: (2025)

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage
di: Li, Na, et al.
Pubblicazione: (2025)

PPBFL: A Privacy Protected Blockchain-based Federated Learning Model
di: Li, Yang, et al.
Pubblicazione: (2024)

Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directions
di: Zhao, Guoshenghui, et al.
Pubblicazione: (2024)

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
di: Wang, Shouju, et al.
Pubblicazione: (2025)

Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy
di: Piran, Fardin Jalil, et al.
Pubblicazione: (2025)

BF-Meta: Secure Blockchain-enhanced Privacy-preserving Federated Learning for Metaverse
di: Liu, Wenbo, et al.
Pubblicazione: (2024)

PRSI: Privacy-Preserving Recommendation Model Based on Vector Splitting and Interactive Protocols
di: Cao, Xiaokai, et al.
Pubblicazione: (2024)