Heimdallr detects seven LLM-induced threat vectors in GitHub CI via L-WPG graphs, triggerability analysis, and hybrid dataflow, with F1 0.917 on 300 labeled workflows and 802 disclosed cases.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2representative citing papers
MAGE uses an agentic shadow memory to proactively detect and mitigate long-horizon threats in LLM agents by distilling safety context and assessing action risks before execution.
citing papers explorer
-
Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows
Heimdallr detects seven LLM-induced threat vectors in GitHub CI via L-WPG graphs, triggerability analysis, and hybrid dataflow, with F1 0.917 on 300 labeled workflows and 802 disclosed cases.
-
MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
MAGE uses an agentic shadow memory to proactively detect and mitigate long-horizon threats in LLM agents by distilling safety context and assessing action risks before execution.