Image de couverture de livre

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Feng, Shanglun, Tramèr, Florian
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
par: Tramèr, Florian, et autres
Publié: (2022)

Evaluations of Machine Learning Privacy Defenses are Misleading
par: Aerni, Michael, et autres
Publié: (2024)

Universal Jailbreak Backdoors from Poisoned Human Feedback
par: Rando, Javier, et autres
Publié: (2023)

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation
par: Küchler, Nicolas, et autres
Publié: (2025)

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
par: Zhang, Jie, et autres
Publié: (2024)

Adversarial Search Engine Optimization for Large Language Models
par: Nestaas, Fredrik, et autres
Publié: (2024)

Membership Inference Attacks on Sequence Models
par: Rossi, Lorenzo, et autres
Publié: (2025)

Evading Black-box Classifiers Without Breaking Eggs
par: Debenedetti, Edoardo, et autres
Publié: (2023)

Privacy Side Channels in Machine Learning Systems
par: Debenedetti, Edoardo, et autres
Publié: (2023)

Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models
par: Zhang, Yiyang, et autres
Publié: (2026)

Blind Baselines Beat Membership Inference Attacks for Foundation Models
par: Das, Debeshee, et autres
Publié: (2024)

On Stealing Graph Neural Network Models
par: Podhajski, Marcin, et autres
Publié: (2025)

Laundering AI Authority with Adversarial Examples
par: Zhang, Jie, et autres
Publié: (2026)

Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
par: Rando, Javier, et autres
Publié: (2025)

Stealix: Model Stealing via Prompt Evolution
par: Zhuang, Zhixiong, et autres
Publié: (2025)

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models
par: Lou, Jiadong, et autres
Publié: (2025)

Model-Guardian: Protecting against Data-Free Model Stealing Using Gradient Representations and Deceptive Predictions
par: Yang, Yunfei, et autres
Publié: (2025)

Black-box Optimization of LLM Outputs by Asking for Directions
par: Zhang, Jie, et autres
Publié: (2025)

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
par: Wen, Yuxin, et autres
Publié: (2024)

Prompt Stealing Attacks Against Text-to-Image Generation Models
par: Shen, Xinyue, et autres
Publié: (2023)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
par: Rando, Javier, et autres
Publié: (2024)

Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
par: Lin, Weilin, et autres
Publié: (2024)

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity
par: Zhu, Zhihao, et autres
Publié: (2023)

Transpose Attack: Stealing Datasets with Bidirectional Training
par: Amit, Guy, et autres
Publié: (2023)

DM4Steal: Diffusion Model For Link Stealing Attack On Graph Neural Networks
par: Chen, Jinyin, et autres
Publié: (2024)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
par: Zhang, Jinghuai, et autres
Publié: (2022)

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
par: Betley, Jan, et autres
Publié: (2025)

Stealing Training Graphs from Graph Neural Networks
par: Lin, Minhua, et autres
Publié: (2024)

Watermark Stealing in Large Language Models
par: Jovanović, Nikola, et autres
Publié: (2024)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
par: Nikolić, Kristina, et autres
Publié: (2025)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
par: Debenedetti, Edoardo, et autres
Publié: (2024)

UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
par: Han, Yuning, et autres
Publié: (2024)

Link Stealing Attacks Against Inductive Graph Neural Networks
par: Wu, Yixin, et autres
Publié: (2024)

Stealthy Imitation: Reward-guided Environment-free Policy Stealing
par: Zhuang, Zhixiong, et autres
Publié: (2024)

Provable Robustness against Backdoor Attacks via the Primal-Dual Perspective on Differential Privacy
par: Saxena, Aman, et autres
Publié: (2026)

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
par: Zhang, Jie, et autres
Publié: (2024)

I Stolenly Swear That I Am Up to (No) Good: Design and Evaluation of Model Stealing Attacks
par: Oliynyk, Daryna, et autres
Publié: (2025)

TrEEStealer: Stealing Decision Trees via Enclave Side Channels
par: Sander, Jonas, et autres
Publié: (2026)

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
par: Bouaziz, Wassim, et autres
Publié: (2025)

Exploring Query Efficient Data Generation towards Data-free Model Stealing in Hard Label Setting
par: Pei, Gaozheng, et autres
Publié: (2024)