3 citations · 3 across the 4 of their papers we have counts for
6 papers
Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
Derui Wang, Zewei Shi, Rayne Holland +4
Debate distillation adapts weaker verifiers using multi-agent debate transcripts to improve their judgement in subsequent debates, but gains on monitored tasks do not establish rel…
When Honesty is Not Enough in AI Debate
Rayne Holland, Liming Zhu, Jason Xue
Scalable oversight aims to verify the behaviour of agents whose capabilities exceed those of their overseers. AI debate has been proposed as an oversight solution in which competin…
TELSAFE: Security Gap Quantitative Risk Assessment Framework
Sarah Ali Siddiqui, Chandra Thapa, Derui Wang +5
Gaps between established security standards and their practical implementation have the potential to introduce vulnerabilities, possibly exposing them to security risks. To effecti…
Private Synthetic Data Generation in Bounded Memory
Rayne Holland, Seyit Camtepe, Chandra Thapa +1
We propose , a lightweight synthetic data generator with \textit{differential privacy} guarantees. uses a novel hierarchical decomposition that a…
Attacking Slicing Network via Side-channel Reinforcement Learning Attack
Wei Shao, Chandra Thapa, Rayne Holland +2
Network slicing in 5G and the future 6G networks will enable the creation of multiple virtualized networks on a shared physical infrastructure. This innovative approach enables the…
Elevating Software Trust: Unveiling and Quantifying the Risk Landscape
Sarah Ali Siddiqui, Chandra Thapa, Rayne Holland +2
Considering the ever-evolving threat landscape and rapid changes in software development, we propose a risk assessment framework called SAFER (Software Analysis Framework for Evalu…