COHORT automates mitigation generation for network attacks via collaborative LLMs on emulated topologies with offensive replay evaluation, reporting 46.7% success rate that is 4.4 times higher than a single-agent baseline.
Optimal defender strategies for CAGE-2 using causal modeling and tree search
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
representative citing papers
In CybORG CAGE-2, programmatic state abstraction improves mean return up to 76% over raw observations while adding deliberation tools to hierarchies degrades performance up to 3.4x and increases token use.
Combines particle filtering, feature-based aggregation, and rollout to produce scalable network security policies with theoretical guarantees that adapt quickly to model changes.
citing papers explorer
-
COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies
COHORT automates mitigation generation for network attacks via collaborative LLMs on emulated topologies with offensive replay evaluation, reporting 46.7% success rate that is 4.4 times higher than a single-agent baseline.
-
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
In CybORG CAGE-2, programmatic state abstraction improves mean return up to 76% over raw observations while adding deliberation tools to hierarchies degrades performance up to 3.4x and increases token use.
-
Adaptive Network Security Policies via Belief Aggregation and Rollout
Combines particle filtering, feature-based aggregation, and rollout to produce scalable network security policies with theoretical guarantees that adapt quickly to model changes.