
context-segmentation
Multi-agent automated context management for long horizon tasks in local AI Agents
ai-securityctfeducation+3
1

Multi-agent automated context management for long horizon tasks in local AI Agents

Zero-retraining sanitization that reorders permutation-equivalent neural network units to destroy malware embedded via weight-steganography attacks…

Self-referenced local contrast for knowledge-poison detection in retrieval-augmented generation

AI Code Security — four agents that catch what SAST misses in AI-generated code. Built on GitLab Duo Agent Platform.

CybORG CAGE 2 environment updated for the paper "Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping"