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.
TrojanPuzzle: Covertly poisoning code-suggestion models
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
The paper formalizes fixed-set worst-case corruption in PBE, implements corruption searches on a string DSL, and shows VPA recovers some margin-1 tasks but fails on public SyGuS where vote margins are near one.
A Dirichlet-prior Bayesian estimator for model success probability replaces Pass@k, delivering faster-converging and more stable rankings with credible intervals on math benchmarks.
A multi-role red-teaming framework with attacker, target, and jury LLMs measures faithfulness in English and Arabic, finding false-premise prompts and length limits change unfaithfulness rates.
Empirical evaluation shows that code generated by all seven tested LLMs contains vulnerabilities, the majority of critical or high severity.
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.
-
Fixed-Set Robustness in Programming by Example: Example Corruption and Semantic Partition Recovery
The paper formalizes fixed-set worst-case corruption in PBE, implements corruption searches on a string DSL, and shows VPA recovers some margin-1 tasks but fails on public SyGuS where vote margins are near one.
-
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
A Dirichlet-prior Bayesian estimator for model success probability replaces Pass@k, delivering faster-converging and more stable rankings with credible intervals on math benchmarks.
-
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
A multi-role red-teaming framework with attacker, target, and jury LLMs measures faithfulness in English and Arabic, finding false-premise prompts and length limits change unfaithfulness rates.
-
Security of LLM-generated Code: A Comparative Analysis
Empirical evaluation shows that code generated by all seven tested LLMs contains vulnerabilities, the majority of critical or high severity.