PRAETORIAN reduces GNN backdoor attack success rate to 0.55% with 0.62% clean accuracy drop by targeting the need for many or highly influential trigger nodes.
Badnets: Identifying vulnerabilities in the machine learning model supply chain
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Testing 18 LLMs found 94.4% vulnerable to direct prompt injection for malware installation, 83.3% to RAG backdoor attacks, and 100% to inter-agent trust exploitation in multi-agent systems.
citing papers explorer
-
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
PRAETORIAN reduces GNN backdoor attack success rate to 0.55% with 0.62% clean accuracy drop by targeting the need for many or highly influential trigger nodes.
-
The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise
Testing 18 LLMs found 94.4% vulnerable to direct prompt injection for malware installation, 83.3% to RAG backdoor attacks, and 100% to inter-agent trust exploitation in multi-agent systems.