David Oygenblik, Teja Akella, Tanmay Gupta, Yanfeng Huang, Brendan Saltaformaggio · ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026 · 2026
DOI: 10.1145/3830454.3846670
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Architectural Backdoors (ABs) have been proposed as a stealthy threat towards secure DL model deployments. ABs hide malicious computation in DL model inference code rather than the model's weights, evading traditional model vetting techniques. However, the practical viability of ABs under real-world deployment conditions has remained unexamined. We show that architectural backdoors are constrained by three fundamental limitations inherent to their trigger detection step: (1) input-space transformations routinely applied during preprocessing corrupt triggers before detection; (2) relaxing detection sensitivity to recover attack success rate inevitably increases false positives, producing observable accuracy degradation (reducing the stealth of the attack); and (3) as trigger complexity grows, the collision space of benign inputs that falsely activate the detector expands, further coupling accuracy loss to attack viability. We formalize these limitations mathematically and introduce FAULT, a framework that enables characterization of the attack-success-rate, accuracy, and false-positive tradeoff space of ABs across varied trigger and detector types. Our evaluation across the GTSRB, Mapillary, and CIFAR10 datasets confirms that architectural backdoors are impractical in realistic deployments.
No comments yet — start the discussion below.