A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
Poisoning language models during instruction tuning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Backdoor attacks aligned with JSON command formats in LLM robot controllers achieve 83% attack success rate while preserving over 93% clean accuracy and sub-second latency.
citing papers explorer
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
From Prompt to Physical Action: Structured Backdoor Attacks on LLM-Mediated Robotic Control Systems
Backdoor attacks aligned with JSON command formats in LLM robot controllers achieve 83% attack success rate while preserving over 93% clean accuracy and sub-second latency.