Descriptor-level manipulation in the Model Context Protocol can drive LLMs to unsafe tool selections in up to 36% of cases; a layered defense of integrity checks, auxiliary-LLM vetting, and runtime guardrails reduces this to 15% and raises blocking to 74%.
Prompt injection 2.0: Hybrid ai threats,
3 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2025 3verdicts
UNVERDICTED 3roles
background 2polarities
background 2representative citing papers
A systematic review of neuro-symbolic AI in cybersecurity finds that deeper integration and causal reasoning improve performance across intrusion detection and vulnerability tasks, while identifying barriers and a research roadmap.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Against Descriptor-Level Manipulation
Descriptor-level manipulation in the Model Context Protocol can drive LLMs to unsafe tool selections in up to 36% of cases; a layered defense of integrity checks, auxiliary-LLM vetting, and runtime guardrails reduces this to 15% and raises blocking to 74%.
-
Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities
A systematic review of neuro-symbolic AI in cybersecurity finds that deeper integration and causal reasoning improve performance across intrusion detection and vulnerability tasks, while identifying barriers and a research roadmap.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.