ATLAS uses large language models to automatically generate formal security properties from threat models and vulnerability databases, detecting 39 of 48 CWEs and producing correct assertions for 33 on three HACK@DAC benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A literature survey concludes that PUF-based and hybrid hardware trust anchors provide the best balance of security, scalability, and cost for AI-enabled IoT systems, while software-only methods are insufficient against physical tampering and cloning.
citing papers explorer
-
ATLAS: AI-Assisted Threat-to-Assertion Learning for System-on-Chip Security Verification
ATLAS uses large language models to automatically generate formal security properties from threat models and vulnerability databases, detecting 39 of 48 CWEs and producing correct assertions for 33 on three HACK@DAC benchmarks.
-
Physically Unclonable Functions for Secure IoT Authentication and Hardware-Anchored AI Model Integrity
A literature survey concludes that PUF-based and hybrid hardware trust anchors provide the best balance of security, scalability, and cost for AI-enabled IoT systems, while software-only methods are insufficient against physical tampering and cloning.