3 papers
cs.CR2026
Observability for Delegated Execution in Agentic AI Systems
Abhinav Mishra, Kumar Sharad
Delegation-scoped execution is not identifiable from standard observables: audit logs and execution traces can be identical under multiple incompatible delegation assignments. This…
cs.CR2018
On the Security of Randomized Defenses Against Adversarial Samples
Kumar Sharad, Giorgia Azzurra Marson, Hien Thi Thu Truong +1
Deep Learning has been shown to be particularly vulnerable to adversarial samples. To combat adversarial strategies, numerous defensive techniques have been proposed. Among these,…
cs.CR2014
An Automated Social Graph De-anonymization Technique
Kumar Sharad, George Danezis
We present a generic and automated approach to re-identifying nodes in anonymized social networks which enables novel anonymization techniques to be quickly evaluated. It uses mach…