Enhancing Human Verification Systems to Address AI Agent Circumvention and Attributability Concerns
Yogev Angelovici, Anish Ganga, Saathvik Kannan, Zihao Zhou · Team MoHacks
Submitted to AI Policy Hackathon at Johns Hopkins University. Sprint projects are early-stage work by participants, not Apart Research publications.
Addressing AI agent attributability concerns using a reworked Public Private Key system to ensure human interaction
Reviews
The certificate based system is innovative. clearly meets a challenge with a workable solution
This Certificate Authority framework presents a novel solution for standardizing methodology in the recognition realm. I am not totally convinced of the political feasability of adoption but in terms of the technical components the project seems feasible and additive
Cite this project
@misc{angelovici2024enhancing,
title = {{Enhancing Human Verification Systems to Address AI Agent Circumvention and Attributability Concerns}},
author = {Yogev Angelovici and Anish Ganga and Saathvik Kannan and Zihao Zhou},
year = {2024},
month = oct,
note = {Submitted to AI Policy Hackathon at Johns Hopkins University, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/enhancing-human-verification-systems-to-address-ai-agent-circumvention-and-attributability-concerns}},
url = {https://apartresearch.com/sprints/projects/enhancing-human-verification-systems-to-address-ai-agent-circumvention-and-attributability-concerns}
}More from AI Policy Hackathon at Johns Hopkins University
- 1st place by peer reviewView project: Robust Machine Unlearning for Dangerous Capabilities
Robust Machine Unlearning for Dangerous Capabilities
Robust Machine Unlearning for Dangerous Capabilities
We test different unlearning methods to make models more robust against exploitation by malicious actors for the creation of bioweapons.
- View project: Infectious Disease Outbreak Prediction and Dashboard
Infectious Disease Outbreak Prediction and Dashboard
Infectious Diseace Dashboards
Our project developed an interactive dashboard to monitor, visualize, and analyze infectious disease outbreaks worldwide. It consolidates historical data from sources like WHO, OWID, and CDC for diseases including …
- View project: Modernizing DC’s Emergency Communications
Modernizing DC’s Emergency Communications
AI-CAD
The District of Columbia proposes implementing an AI-enabled Computer-Aided Dispatch (CAD) system to address critical deficiencies in our current emergency alert infrastructure. This policy establishes a framework for …