Adelin Travers
YOU?
Author Swipe
View article: A2AS: Agentic AI Runtime Security and Self-Defense
A2AS: Agentic AI Runtime Security and Self-Defense Open
View article: Interpretability in Safety-Critical FinancialTrading Systems
Interpretability in Safety-Critical FinancialTrading Systems Open
Sophisticated machine learning (ML) models to inform trading in the financial sector create problems of interpretability and risk management. Seemingly robust forecasting models may behave erroneously in out of distribution settings. In 20…
View article: SoK: Machine Learning Governance
SoK: Machine Learning Governance Open
The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society. In this paper, we develop the concept of ML governance to balance such benefits and risks, with the aim of achieving …
View article: On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples
On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples Open
Machine learning (ML) models are known to be vulnerable to adversarial examples. Applications of ML to voice biometrics authentication are no exception. Yet, the implications of audio adversarial examples on these real-world systems remain…
View article: Machine Unlearning
Machine Unlearning Open
Once users have shared their data online, it is generally difficult for them
to revoke access and ask for the data to be deleted. Machine learning (ML)
exacerbates this problem because any model trained with said data may have
memorized it…
View article: Machine Unlearning
Machine Unlearning Open
Once users have shared their data online, it is generally difficult for them to revoke access and ask for the data to be deleted. Machine learning (ML) exacerbates this problem because any model trained with said data may have memorized it…