8 papers
DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion
Hossein Mirzaei, Zeinab Taghavi, Sepehr Rezaee +3
Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safet…
A Contrastive Teacher-Student Framework for Novelty Detection under Style Shifts
Hossein Mirzaei, Mojtaba Nafez, Moein Madadi +12
There have been several efforts to improve Novelty Detection (ND) performance. However, ND methods often suffer significant performance drops under minor distribution shifts caused…
Scanning Trojaned Models Using Out-of-Distribution Samples
Hossein Mirzaei, Ali Ansari, Bahar Dibaei Nia +10
Scanning for trojan (backdoor) in deep neural networks is crucial due to their significant real-world applications. There has been an increasing focus on developing effective gener…
RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples
Hossein Mirzaei, Mohammad Jafari, Hamid Reza Dehbashi +7
In recent years, there have been significant improvements in various forms of image outlier detection. However, outlier detection performance under adversarial settings lags far be…
Mitigating Spurious Negative Pairs for Robust Industrial Anomaly Detection
Hossein Mirzaei, Mojtaba Nafez, Jafar Habibi +2
Despite significant progress in Anomaly Detection (AD), the robustness of existing detection methods against adversarial attacks remains a challenge, compromising their reliability…
Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddings
Hossein Mirzaei, Mackenzie W. Mathis
Despite significant advancements in out-of-distribution (OOD) detection, existing methods still struggle to maintain robustness against adversarial attacks, compromising their reli…