HTell detects backdoors by random probing of the model head, reporting 99.03% true positive rate and 2.11% false positive rate at 12.69 ms per model on a benchmark of over 6700 models.
Lira: Learnable, imperceptible and robust backdoor attacks,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
DFBScanner detects backdoors by combining anomaly indicators from final-layer parameters into a Trojan clue score, reporting 97.17% true-positive rate, 0.95% false-positive rate, and 1 ms average detection time on a benchmark of over 5,000 models.
Catastrophic overfitting in fast adversarial training is reinterpreted as a weak-trigger variant of unlearnable tasks, allowing backdoor-inspired recalibration and outlier suppression to restore robustness.
citing papers explorer
-
Fast and Lightweight Backdoor Detection via Head Random Probing
HTell detects backdoors by random probing of the model head, reporting 99.03% true positive rate and 2.11% false positive rate at 12.69 ms per model on a benchmark of over 6700 models.
-
Lightweight and Fast Backdoor Model Detection
DFBScanner detects backdoors by combining anomaly indicators from final-layer parameters into a Trojan clue score, reporting 97.17% true-positive rate, 0.95% false-positive rate, and 1 ms average detection time on a benchmark of over 5,000 models.
-
Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Training
Catastrophic overfitting in fast adversarial training is reinterpreted as a weak-trigger variant of unlearnable tasks, allowing backdoor-inspired recalibration and outlier suppression to restore robustness.