Blog

---

• How to prompt LLMs with private data?

  by Haonan Duan, Adam Dziedzic, Nicolas Papernot, Franziska Boenisch, and Jovana Jankovic

• Can stochastic pre-processing defenses protect your models?

  by Yue Gao, Ilia Shumailov, Kassem Fawaz, and Nicolas Papernot.

• Are adversarial examples against proof-of-learning adversarial?

  by Congyu Fang, Hengrui Jia, Varun Chandrasekaran, and Nicolas Papernot

• How to Keep a Model Stealing Adversary Busy?

  by Adam Dziedzic, Muhammad Ahmad Kaleem, and Nicolas Papernot

• All You Need Is Matplotlib

  or Federated Learning with Untrusted Servers is Not Private

• Arbitrating the integrity of stochastic gradient descent with proof-of-learning

  by Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, and Nicolas Papernot

• Beyond federation: collaborating in ML with confidentiality and privacy

  by Adam Dziedzic, Christopher A. Choquette-Choo, Natalie Dullerud and Nicolas Papernot

• Is this model mine?

  by Pratyush Maini, Mohammad Yaghini and Nicolas Papernot

• To guarantee privacy, focus on the algorithms, not the data

  by Aleksandar Nikolov and Nicolas Papernot

• Teaching Machines to Unlearn

  by Christopher A. Choquette-Choo, Varun Chandrasekaran, and Nicolas Papernot

• In Model Extraction, Don’t Just Ask ‘How?’: Ask ‘Why?’

  by Matthew Jagielski and Nicolas Papernot

• How to steal modern NLP systems with gibberish?

  by Kalpesh Krishna and Nicolas Papernot

• How to know when machine learning does not know

  by Nicolas Papernot and Nicholas Frosst

• Machine Learning with Differential Privacy in TensorFlow

  by Nicolas Papernot

• Privacy and machine learning: two unexpected allies?

  by Nicolas Papernot and Ian Goodfellow

• The challenge of verification and testing of machine learning

  by Ian Goodfellow and Nicolas Papernot

• Is attacking machine learning easier than defending it?

  by Ian Goodfellow and Nicolas Papernot

• Breaking things is easy

  by Nicolas Papernot and Ian Goodfellow