9 papers
Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3
Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protect…
Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models
Mojtaba Nafez, James Henderson
Uniform-state diffusion models (USDMs) can revise any token at any denoising step, which lets them correct their own mistakes, a key advantage over masked diffusion. Self-correctio…
GhostWord: A Fine-Grained Backdoor Attack on Automatic Speech Recognition
Mojtaba Nafez, Mobina Poulaei, Kiarash Kiani Feriz +4
Automatic Speech Recognition (ASR) systems are widely deployed in safety-critical settings but remain vulnerable to data-poisoning backdoor attacks. Existing ASR backdoors typicall…
FrameShield: Adversarially Robust Video Anomaly Detection
Mojtaba Nafez, Mobina Poulaei, Nikan Vasei +3
Weakly Supervised Video Anomaly Detection (WSVAD) has achieved notable advancements, yet existing models remain vulnerable to adversarial attacks, limiting their reliability. Due t…
PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies
Mojtaba Nafez, Amirhossein Koochakian, Arad Maleki +2
Anomaly Detection (AD) and Anomaly Localization (AL) are crucial in fields that demand high reliability, such as medical imaging and industrial monitoring. However, current AD and…
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…
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…
Universal Novelty Detection Through Adaptive Contrastive Learning
Hossein Mirzaei, Mojtaba Nafez, Mohammad Jafari +5
Novelty detection is a critical task for deploying machine learning models in the open world. A crucial property of novelty detection methods is universality, which can be interpre…