Publications

954 results for Trustworthy AI

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
- - Zhi-yi Chin
  - Chieh-ming Jiang
  - et al.
- 2024
- ICML 2024
Conference paper
What Would Gauss Say About Representations? Probing Pretrained Image Models using Synthetic Gaussian Benchmarks
- - Irene Ko
  - Pin-Yu Chen
  - et al.
- 2024
- ICML 2024
Conference paper
Slicing Mutual Information Generalization Bounds for Neural Networks
- - Kimia Nadjahi
  - Kristjan Greenewald
  - et al.
- 2024
- ICML 2024
Conference paper
Trust Regions for Explanations via Black-Box Probabilistic Certification
- - Amit Dhurandhar
  - Swagatam Haldar
  - et al.
- 2024
- ICML 2024
Conference paper
Thermometer: Towards Universal Calibration for Large Language Models
- - Maohao Shen
  - Subhro Das
  - et al.
- 2024
- ICML 2024
Conference paper
CharED: Character-wise Ensemble Decoding for Large Language Models
- - Kevin Gu
  - Eva Tuecke
  - et al.
- 2024
- ICML 2024
Workshop paper
Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
- - Swanand Ravindra Kadhe
  - Farhan Ahmed
  - et al.
- 2024
- ICML 2024
Workshop paper
Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation
- - Tomas Bueno Momcilovic
  - Beat Buesser
  - et al.
- 2024
- xAI 2024
Workshop paper
AUTOLYCUS: Exploiting Explainable Artificial Intelligence (XAI) for Model Extraction Attacks against Interpretable Models
- - Abdullah Caglar Oksuz
  - Anisa Halimi
  - et al.
- 2024
- PETS 2024
Conference paper
Exploring Vulnerabilities in LLMs: A Red Teaming Approach to Evaluate Social Bias
- - Yuya Jeremy Ong
  - Jay Pankaj Gala
  - et al.
- 2024
- IEEE CISOSE 2024
Conference paper