Michael Backes

Swarm Learning for decentralized and confidential clinical machine learning

2021 · 801 Zit. · Nature

In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT

2023 · 71 Zit. · arXiv (Cornell University)

TrustLLM: Trustworthiness in Large Language Models

2024 · 50 Zit. · arXiv (Cornell University)

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

2021 · 46 Zit. · arXiv (Cornell University)

Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning

2020 · 16 Zit. · arXiv (Cornell University)

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

2024 · 3 Zit.

How many winning tickets are there in one DNN?

2020 · 2 Zit. · arXiv (Cornell University)

Voice Jailbreak Attacks Against GPT-4o

2024 · 2 Zit. · arXiv (Cornell University)

Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models

2023 · 2 Zit. · arXiv (Cornell University)

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

2024 · 0 Zit. · arXiv (Cornell University)