Search Results for author:
Found 3 papers, 0 papers with code
AI Risk Management Should Incorporate Both Safety and Security
The exposure of security vulnerabilities in safety-aligned language models, e. g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security.
What's in Your "Safe" Data?: Identifying Benign Data that Breaks Safety
Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking.
Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions
We categorize sources of discrimination in the ML pipeline into two classes: aleatoric discrimination, which is inherent in the data distribution, and epistemic discrimination, which is due to decisions made during model development.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
