Copertina

Evaluations of Machine Learning Privacy Defenses are Misleading

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Aerni, Michael, Zhang, Jie, Tramèr, Florian
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Membership Inference Attacks on Sequence Models
di: Rossi, Lorenzo, et al.
Pubblicazione: (2025)

Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
di: Zhang, Jie, et al.
Pubblicazione: (2024)

Privacy Backdoors: Stealing Data with Corrupted Pretrained Models
di: Feng, Shanglun, et al.
Pubblicazione: (2024)

AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2024)

Large-scale online deanonymization with LLMs
di: Lermen, Simon, et al.
Pubblicazione: (2026)

Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
di: Rando, Javier, et al.
Pubblicazione: (2025)

Privacy Side Channels in Machine Learning Systems
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2023)

Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data
di: Zhang, Jie, et al.
Pubblicazione: (2024)

Laundering AI Authority with Adversarial Examples
di: Zhang, Jie, et al.
Pubblicazione: (2026)

Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
di: Tramèr, Florian, et al.
Pubblicazione: (2022)

Blind Baselines Beat Membership Inference Attacks for Foundation Models
di: Das, Debeshee, et al.
Pubblicazione: (2024)

Black-box Optimization of LLM Outputs by Asking for Directions
di: Zhang, Jie, et al.
Pubblicazione: (2025)

Adversarial Search Engine Optimization for Large Language Models
di: Nestaas, Fredrik, et al.
Pubblicazione: (2024)

Evading Black-box Classifiers Without Breaking Eggs
di: Debenedetti, Edoardo, et al.
Pubblicazione: (2023)

The Jailbreak Tax: How Useful are Your Jailbreak Outputs?
di: Nikolić, Kristina, et al.
Pubblicazione: (2025)

Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory?
di: Aerni, Michael, et al.
Pubblicazione: (2025)

Combining Machine Learning Defenses without Conflicts
di: Duddu, Vasisht, et al.
Pubblicazione: (2024)

Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning
di: Damie, Marc, et al.
Pubblicazione: (2025)

Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors
di: Wang, Tianchun, et al.
Pubblicazione: (2024)

Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
di: Naseh, Ali, et al.
Pubblicazione: (2025)

Agentic Privacy-Preserving Machine Learning
di: Zhang, Mengyu, et al.
Pubblicazione: (2025)

Universal Jailbreak Backdoors from Poisoned Human Feedback
di: Rando, Javier, et al.
Pubblicazione: (2023)

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
di: Nasr, Milad, et al.
Pubblicazione: (2025)

Machine Learning with Privacy for Protected Attributes
di: Mahloujifar, Saeed, et al.
Pubblicazione: (2025)

SoK: Unintended Interactions among Machine Learning Defenses and Risks
di: Duddu, Vasisht, et al.
Pubblicazione: (2023)

FT-PrivacyScore: Personalized Privacy Scoring Service for Machine Learning Participation
di: Gu, Yuechun, et al.
Pubblicazione: (2024)

A Defensive Framework Against Adversarial Attacks on Machine Learning-Based Network Intrusion Detection Systems
di: Tafreshian, Benyamin, et al.
Pubblicazione: (2025)

Decentralised, Collaborative, and Privacy-preserving Machine Learning for Multi-Hospital Data
di: Fang, Congyu, et al.
Pubblicazione: (2024)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
di: Paracha, Anum, et al.
Pubblicazione: (2025)

PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
di: Kazmi, Mishaal, et al.
Pubblicazione: (2024)

Calibrating Practical Privacy Risks for Differentially Private Machine Learning
di: Gu, Yuechun, et al.
Pubblicazione: (2024)

Does Training with Synthetic Data Truly Protect Privacy?
di: Zhao, Yunpeng, et al.
Pubblicazione: (2025)

On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
di: Wang, Zijian, et al.
Pubblicazione: (2025)

An Adversarial Perspective on Machine Unlearning for AI Safety
di: Łucki, Jakub, et al.
Pubblicazione: (2024)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
di: Carlini, Nicholas, et al.
Pubblicazione: (2025)

Bridging Privacy and Robustness for Trustworthy Machine Learning
di: Zhang, Xiaojin, et al.
Pubblicazione: (2024)

A Novel Review of Stability Techniques for Improved Privacy-Preserving Machine Learning
di: DuPlessie, Coleman, et al.
Pubblicazione: (2024)

The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning
di: Wei, Yu, et al.
Pubblicazione: (2023)

AIJack: Let's Hijack AI! Security and Privacy Risk Simulator for Machine Learning
di: Takahashi, Hideaki
Pubblicazione: (2023)

SFPDML: Securer and Faster Privacy-Preserving Distributed Machine Learning based on MKTFHE
di: Wang, Hongxiao, et al.
Pubblicazione: (2022)