works on

From the 1 of 7 linked papers with an AI index.

activity
20242026
collaborators

7 papers

cs.IR2026

With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots

Zeinab Sadat Taghavi, Ali Modarressi, Hinrich Schutze +1

The paper identifies blind spots in neural retrievers used for retrieval‑augmented generation, where relevant entities are missed due to low embedding similarity, and proposes an u…

cs.CL2025

ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge

Zeinab Sadat Taghavi, Ali Modarressi, Yunpu Ma +1

Retrieval systems are central to many NLP pipelines, but often rely on surface-level cues such as keyword overlap and lexical semantic similarity. To evaluate retrieval beyond thes…

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.LG2025

Killing it with Zero-Shot: Adversarially Robust Novelty Detection

Hossein Mirzaei, Mohammad Jafari, Hamid Reza Dehbashi +3

Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen data during model inference. This capability is especially important for the safe and r…