Large-scale study on 60k firmware shows vulnerable function versions, search space, function sizes and compilation toolchains affect BCSD performance; build-aware queries raise MRR from 0.818 to 0.981 and TPL-aware two-stage search improves it by 18.5%.
Nguyen, Kandaraj Piamrat, Guido Marchetto, and Quoc-Viet Pham
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.
citing papers explorer
-
Understanding Binary Code Similarity for Real-World Vulnerability Detection: A Large-Scale Empirical Study
Large-scale study on 60k firmware shows vulnerable function versions, search space, function sizes and compilation toolchains affect BCSD performance; build-aware queries raise MRR from 0.818 to 0.981 and TPL-aware two-stage search improves it by 18.5%.
-
Protecting On-Device AI Inference: A Systematic Review of Attacks and Defence Mechanisms
A systematic review of on-device AI inference security finds defenses are imbalanced, with roughly half focused on IP theft while one-third of attacks (adversarial examples) lack any associated defenses.