Publications (7)
Scalable and Anonymous Modeling of Large Populations of Flexible Appliances
Mahnoosh Alizadeh, Anna Scaglione, Andy Applebaum +2
To respond to volatility and congestion in the power grid, demand response (DR) mechanisms allow for shaping the load compared to a base load profile. When tapping on a large popul…
EVMbench: Evaluating AI Agents on Smart Contract Security
Justin Wang, Andreas Bigger, Xiaohai Xu +5
Smart contracts on public blockchains now manage large amounts of value, and vulnerabilities in these systems can lead to substantial losses. As AI agents become more capable at re…
Towards Causal Models for Adversary Distractions
Ron Alford, Andy Applebaum
Automated adversary emulation is becoming an indispensable tool of network security operators in testing and evaluating their cyber defenses. At the same time, it has exposed how q…
Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies
Melody Wolk, Andy Applebaum, Camron Dennler +8
Advancements in reinforcement learning (RL) have inspired new directions in intelligent automation of network defense. However, many of these advancements have either outpaced thei…
OpenAI GPT-5 System Card
Aaditya Singh, Adam Fry, Adam Perelman +483
This is the system card published alongside the OpenAI GPT-5 launch, August 2025. GPT-5 is a unified system with a smart and fast model that answers most questions, a deeper reason…
OpenAI o1 System Card
OpenAI, :, Aaron Jaech +261
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought. These advanced reasoning capabilities provide new avenues for improving the…