29 citations · 90 across the 24 of their papers we have counts for
27 papers
From Normative Frameworks to Alignment Data: Constructing and Evaluating SFT and Preference Data
Husrev Taha Sencar, Rezart Beka, Danish Naeem +6
Aligning language models with a specified normative framework requires translating abstract principles into concrete examples and preference signals from which models can learn. We…
Beyond Cultural Knowledge: Evaluating Arabic Cultural Appropriateness of Large Language Models
Enes Altinisik, Hamdy Mubarak, Masoomali Fatehkia +1
Large language models (LLMs) increasingly serve users whose expectations are shaped by their cultural context, yet most cultural evaluations test what a model knows rather than how…
Fanar 2.0: Arabic Generative AI Stack
FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad +34
We present Fanar 2.0, the second generation of Qatar's Arabic-centric Generative AI platform. Sovereignty is a first-class design principle: every component, from data pipelines to…
There Is More to Refusal in Large Language Models than a Single Direction
Faaiz Joad, Majd Hawasly, Sabri Boughorbel +2
Prior work argues that refusal in large language models is mediated by a single direction, enabling steering and abliteration. We show that this account is incomplete: across diver…
Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction
Enes Altinisik, Masoomali Fatehkia, Fatih Deniz +4
Factual hallucination remains a central challenge for large language models (LLMs). Existing mitigation approaches primarily rely on either external post-hoc verification or mappin…
FanarGuard: A Culturally-Aware Moderation Filter for Arabic Language Models
Masoomali Fatehkia, Enes Altinisik, Husrev Taha Sencar
Content moderation filters are a critical safeguard against alignment failures in language models. Yet most existing filters focus narrowly on general safety and overlook cultural…
Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
Asim Ersoy, Enes Altinisik, Husrev Taha Sencar +1
Tool calling is a critical capability that allows Large Language Models (LLMs) to interact with external systems, significantly expanding their utility. However, research and resou…
From Text to Actionable Intelligence: Automating STIX Entity and Relationship Extraction
Ahmed Lekssays, Husrev Taha Sencar, Ting Yu
Sharing methods of attack and their effectiveness is a cornerstone of building robust defensive systems. Threat analysis reports, produced by various individuals and organizations,…
PAM: Training Policy-Aligned Moderation Filters at Scale
Masoomali Fatehkia, Enes Altinisik, Mohamed Osman +1
Large language models (LLMs) remain vulnerable to misalignment and jailbreaks, making external safeguards like moderation filters essential, yet existing filters often focus narrow…
TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text
Ahmed Lekssays, Utsav Shukla, Husrev Taha Sencar +1
Accurately identifying adversarial techniques in security texts is critical for effective cyber defense. However, existing methods face a fundamental trade-off: they either rely on…
Fanar: An Arabic-Centric Multimodal Generative AI Platform
Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad +39
We present Fanar, a platform for Arabic-centric multimodal generative AI systems, that supports language, speech and image generation tasks. At the heart of Fanar are Fanar Star an…
Explaining the role of Intrinsic Dimensionality in Adversarial Training
Enes Altinisik, Safa Messaoud, Husrev Taha Sencar +2
Adversarial Training (AT) impacts different architectures in distinct ways: vision models gain robustness but face reduced generalization, encoder-based models exhibit limited robu…
Semantic Ranking for Automated Adversarial Technique Annotation in Security Text
Udesh Kumarasinghe, Ahmed Lekssays, Husrev Taha Sencar +3
We introduce a new method for extracting structured threat behaviors from threat intelligence text. Our method is based on a multi-stage ranking architecture that allows jointly op…
ProvG-Searcher: A Graph Representation Learning Approach for Efficient Provenance Graph Search
Enes Altinisik, Fatih Deniz, Husrev Taha Sencar
We present ProvG-Searcher, a novel approach for detecting known APT behaviors within system security logs. Our approach leverages provenance graphs, a comprehensive graph represent…
A3T: Accuracy Aware Adversarial Training
Enes Altinisik, Safa Messaoud, Husrev Taha Sencar +1
Adversarial training has been empirically shown to be more prone to overfitting than standard training. The exact underlying reasons still need to be fully understood. In this pape…
GREENER: Graph Neural Networks for News Media Profiling
Panayot Panayotov, Utsav Shukla, Husrev Taha Sencar +2
We study the problem of profiling news media on the Web with respect to their factuality of reporting and bias. This is an important but under-studied problem related to disinforma…
Impact of Adversarial Training on Robustness and Generalizability of Language Models
Enes Altinisik, Hassan Sajjad, Husrev Taha Sencar +2
Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and gener…
Ten Years after ImageNet: A 360° Perspective on AI
Sanjay Chawla, Preslav Nakov, Ahmed Ali +7
It is ten years since neural networks made their spectacular comeback. Prompted by this anniversary, we take a holistic perspective on Artificial Intelligence (AI). Supervised Lear…
Exploration of Enterprise Server Data to Assess Ease of Modeling System Behavior
Enes Altinisik, Husrev Taha Sencar, Mohamed Nabeel +2
Enterprise networks are one of the major targets for cyber attacks due to the vast amount of sensitive and valuable data they contain. A common approach to detecting attacks in the…
Video Source Characterization Using Encoding and Encapsulation Characteristics
Enes Altinisik, Husrev Taha Sencar, Diram Tabaa
We introduce a new method for camera-model identification. Our approach combines two independent aspects of video file generation corresponding to video coding and media data encap…
Automatic Generation of H.264 Parameter Sets to Recover Video File Fragments
Enes Altinisik, Hüsrev Taha Sencar
We address the problem of decoding video file fragments when the necessary encoding parameters are missing. With this objective, we propose a method that automatically generates H.…
BLEKeeper: Response Time Behavior Based Man-In-The-Middle Attack Detection
Muhammed Ali Yurdagul, Husrev Taha Sencar
Bluetooth Low Energy (BLE) has become one of the most popular wireless communication protocols and is used in billions of smart devices. Despite several security features, the hard…
A Survey on Predicting the Factuality and the Bias of News Media
Preslav Nakov, Husrev Taha Sencar, Jisun An +1
The present level of proliferation of fake, biased, and propagandistic content online has made it impossible to fact-check every single suspicious claim or article, either manually…
Estimating Uniqueness of I-Vector Representation of Human Voice
Erkam Sinan Tandogan, Husrev Taha Sencar
We study the individuality of the human voice with respect to a widely used feature representation of speech utterances, namely, the i-vector model. As a first step toward this goa…