Benchmark RadarEXE-Bench
EXE-Bench evaluates AI-based Windows malware detectors on performance, temporal robustness, adversarial robustness, and computational overhead, aggregated into a single score.
- Released
- 2026-07-27
- Readiness
- Paper only
- Primary field
- Cybersecurity
Why it matters
Provides a comprehensive benchmark to guide deployment decisions, highlighting tradeoffs between feature-engineered and deep network detectors.
Motivation
Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their britt…
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.