Publications

This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.

Date

Start

End

Featured collections

Popular topics

673 results for Trustworthy AI

Stress-Testing Bias Mitigation Algorithms to Understand Fairness Vulnerabilities
- - Karan Bhanot
  - Ioana Baldini
  - et al.
- 2023
- AIES 2023
Interpretable Differencing of Machine Learning Models
- - Swagatam Haldar
  - Diptikalyan Saha
  - et al.
- 2023
- UAI 2023
Pessimistic Model Selection for Deep Reinforcement Learning
- - Chao-Han Huck Yang
  - Zhengling Qi
  - et al.
- 2023
- UAI 2023
Code Vulnerability Detection via Signal-Aware Learning
- - Sahil Suneja
  - Yufan Zhuang
  - et al.
- 2023
- EuroS&P 2023
DetAIL: A Tool to Automatically Detect and Analyze Drift In Language
- - Nishtha Madaan
  - Adithya Manjunatha
  - et al.
- 2023
- IAAI 2023
Generating One-Hot Maps under Encryption
- - Ehud Aharoni
  - Nir Drucker
  - et al.
- 2023
- CSCML 2023
How to Backdoor Diffusion Models?
- - Sheng-yen Cho
  - Pin-Yu Chen
  - et al.
- 2023
- CVPR 2023
Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations
- - Lei Hsiung
  - Yun-Yun Tsai
  - et al.
- 2023
- CVPR 2023
Trustworthy AI and the Logics of Intersectional Resistance
- - Bran Knowles
  - Jasmine Fledderjohann
  - et al.
- 2023
- FAccT 2023
Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation
- - Neel Bhandari
  - Pin-Yu Chen
- 2023
- ICASSP 2023