collaborators

8 papers

cs.CV2025

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…

cs.CV2025

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…

cs.LG2025

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…

cs.CV2025

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…

cs.CV2025

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…

cs.LG2025

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…