Publications

This is our catalog of recent publications authored by IBM researchers, in collaboration with the global research community. We’re currently adding our back catalog of more than 110,000 publications. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.

Featured collections

Popular topics

Year

415 results for Trustworthy AI

Understanding the Limits of Unsupervised Domain Adaptation via Data Poisoning
- - Akshay Mehra
  - Bhavya Kailkhura
  - et al.
- 2021
- NeurIPS 2021
Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing
- - Aadarsh Sahoo
  - Rutav Shah
  - et al.
- 2021
- NeurIPS 2021
When does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
- - Lijie Fan
  - Sijia Liu
  - et al.
- 2021
- NeurIPS 2021
Robust Deep Reinforcement Learning through Adversarial Loss
- - Tuomas Oikarinen
  - Wang Zhang
  - et al.
- 2021
- NeurIPS 2021
Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception
- - Joel Dapello
  - Jenelle Feather
  - et al.
- 2021
- NeurIPS 2021
Post-processing for Individual Fairness
- - Felix Petersen
  - Debarghya Mukherjee
  - et al.
- 2021
- NeurIPS 2021
LEGATO: A LayerwisE Gradient AggregaTiOn Algorithm for Mitigating Byzantine Attacks in Federated Learning
- - Kamala Varma
  - Yi Zhou
  - et al.
- 2021
- CLOUD 2021
Characteristic Examples: High-Robustness, Low-Transferability Fingerprinting of Neural Networks
- - Siyue Wang
  - Xiao Wang
  - et al.
- 2021
- IJCAI 2021
Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Models
- - Xiao Zang
  - Yi Xie
  - et al.
- 2021
- IJCAI 2021
InfoSurgeon: Cross-Media Fine-grained Information Consistency Checking for Fake News Detection
- - Yi Fung
  - Chris Thomas
  - et al.
- 2021
- ACL-IJCNLP 2021