1 option
2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) / Amartya Sanyal.
- Format:
- Book
- Author/Creator:
- Sanyal, Amartya, author.
- Language:
- English
- Subjects (All):
- Machine learning--Congresses.
- Machine learning.
- Machine learning--Development.
- Physical Description:
- 1 Online-Ressource Illustrationen
- Place of Publication:
- Piscataway, NJ : IEEE Computer Society, 2024.
- Contents:
- Half Title Page
- Title Page
- Copyright Page
- Table of Contents
- Message from the Program Chairs
- Organizing Committee
- Program Committee
- Steering Committee
- Non-Halting Queries: Exploiting Fixed Points in LLMs
- Jailbreaking Black Box Large Language Models in Twenty Queries
- Get My Drift? Catching LLM Task Drift with Activation Deltas
- MARKMyWORDS: Analyzing and Evaluating Language Model Watermarks
- SnatchML: Hijacking ML Models Without Training Access
- TS-Inverse: A Gradient Inversion Attack Tailored for Federated Time Series Forecasting Models.
- Notes:
- Description based on publisher supplied metadata and other sources.
- ISBN:
- 979-83-315-1711-3
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.