Imagen de Portada

Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Rashid, Md Rafi Ur, Dasu, Vishnu Asutosh, Gu, Kang, Sultana, Najrin, Mehnaz, Shagufta
Formato:	Preprint
Publicado:	2023
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Forget to Flourish: Leveraging Machine-Unlearning on Pretrained Language Models for Privacy Leakage
por: Rashid, Md Rafi Ur, et al.
Publicado: (2024)

Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models
por: Gu, Kang, et al.
Publicado: (2024)

From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generation
por: Sultana, Najrin, et al.
Publicado: (2025)

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

Heimdall: Formally Verified Automated Migration of Legacy eBPF Programs to Rust
por: Dasu, Vishnu Asutosh, et al.
Publicado: (2026)

Chain-of-Thought Driven Adversarial Scenario Extrapolation for Robust Language Models
por: Rashid, Md Rafi Ur, et al.
Publicado: (2025)

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks
por: Rashid, Md Rafi Ur, et al.
Publicado: (2026)

LogicEval: A Systematic Framework for Evaluating Automated Repair Techniques for Logical Vulnerabilities in Real-World Software
por: Rashid, Syed Md Mukit, et al.
Publicado: (2026)

Attacks Meet Interpretability (AmI) Evaluation and Findings
por: Ma, Qian, et al.
Publicado: (2023)

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
por: Song, Zeyu, et al.
Publicado: (2023)

Baiting AI: Deceptive Adversary Against AI-Protected Industrial Infrastructures
por: Pasikhani, Aryan, et al.
Publicado: (2026)

iResolveX: Multi-Layered Indirect Call Resolution via Static Reasoning and Learning-Augmented Refinement
por: Santra, Monika, et al.
Publicado: (2026)

Analysis of Privacy Leakage in Federated Large Language Models
por: Vu, Minh N., et al.
Publicado: (2024)

Real-Time Privacy Risk Measurement with Privacy Tokens for Gradient Leakage
por: Meng, Jiayang, et al.
Publicado: (2025)

Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
por: Meng, Jiayang, et al.
Publicado: (2025)

The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning
por: Xiang, Kunlan, et al.
Publicado: (2025)

SoK: On Gradient Leakage in Federated Learning
por: Du, Jiacheng, et al.
Publicado: (2024)

PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning
por: Hou, Sizai, et al.
Publicado: (2024)

Anti-Tamper Radio meets Reconfigurable Intelligent Surface for System-Level Tamper Detection
por: Tabar, Maryam Shaygan, et al.
Publicado: (2025)

Building Gradient Bridges: Label Leakage from Restricted Gradient Sharing in Federated Learning
por: Zhang, Rui, et al.
Publicado: (2024)

Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
por: Fan, Mingyuan, et al.
Publicado: (2022)

Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation
por: Shi, Haonan, et al.
Publicado: (2025)

Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks
por: Zheng, Lele, et al.
Publicado: (2024)

Random Gradient Masking as a Defensive Measure to Deep Leakage in Federated Learning
por: Kim, Joon, et al.
Publicado: (2024)

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
por: Wang, Zhibo, et al.
Publicado: (2024)

Computing Maximal Per-Record Leakage and Leakage-Distortion Functions for Privacy Mechanisms under Entropy-Constrained Adversaries
por: Wu, Genqiang, et al.
Publicado: (2026)

Membership Information Leakage in Federated Contrastive Learning
por: Chen, Kongyang, et al.
Publicado: (2024)

Enhancing Security Using Random Binary Weights in Privacy-Preserving Federated Learning
por: Sawada, Hiroto, et al.
Publicado: (2024)

Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks
por: Eltaras, Tamer Ahmed, et al.
Publicado: (2025)

SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learning
por: Li, Borui, et al.
Publicado: (2025)

A Technique for the Detection of PDF Tampering or Forgery
por: Grobler, Gabriel, et al.
Publicado: (2025)

Evidence Tampering and Chain of Custody in Layered Attestations
por: Kretz, Ian D., et al.
Publicado: (2024)

CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
por: Wang, Weiqi, et al.
Publicado: (2025)

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
por: Ganev, Georgi, et al.
Publicado: (2025)

PrivTru: A Privacy-by-Design Data Trustee Minimizing Information Leakage
por: Gehring, Lukas, et al.
Publicado: (2025)

Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set
por: Fu, Jie, et al.
Publicado: (2026)

Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelines
por: Huang, Tao, et al.
Publicado: (2026)

Defeating Cerberus: Concept-Guided Privacy-Leakage Mitigation in Multimodal Language Models
por: Zhang, Boyang, et al.
Publicado: (2025)

B-Privacy: Defining and Enforcing Privacy in Weighted Voting
por: Breckenridge, Samuel, et al.
Publicado: (2025)

LADSG: Label-Anonymized Distillation and Similar Gradient Substitution for Label Privacy in Vertical Federated Learning
por: Yan, Zeyu, et al.
Publicado: (2025)