Husrev Taha Sencar

Sanjay Chawla, Preslav Nakov, Ahmed Ali et al. · berkeley

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 Learning for cognitive tasks is effectively solved - provided we have enough high-quality labeled data. However, deep neural network models are not easily interpretable, and thus the debate between blackbox and whitebox modeling has come to the fore. The rise of attention networks, self-supervised learning, generative modeling, and graph neural networks has widened the application space of AI. Deep Learning has also propelled the return of reinforcement learning as a core building block of autonomous decision making systems. The possible harms made possible by new AI technologies have raised socio-technical issues such as transparency, fairness, and accountability. The dominance of AI by Big-Tech who control talent, computing resources, and most importantly, data may lead to an extreme AI divide. Failure to meet high expectations in high profile, and much heralded flagship projects like self-driving vehicles could trigger another AI winter.

Panayot Panayotov, Utsav Shukla, Husrev Taha Sencar et al.

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 disinformation and "fake news" detection, but it addresses the issue at a coarser granularity compared to looking at an individual article or an individual claim. This is useful as it allows to profile entire media outlets in advance. Unlike previous work, which has focused primarily on text (e.g.,~on the text of the articles published by the target website, or on the textual description in their social media profiles or in Wikipedia), here our main focus is on modeling the similarity between media outlets based on the overlap of their audience. This is motivated by homophily considerations, i.e.,~the tendency of people to have connections to people with similar interests, which we extend to media, hypothesizing that similar types of media would be read by similar kinds of users. In particular, we propose GREENER (GRaph nEural nEtwork for News mEdia pRofiling), a model that builds a graph of inter-media connections based on their audience overlap, and then uses graph neural networks to represent each medium. We find that such representations are quite useful for predicting the factuality and the bias of news media outlets, yielding improvements over state-of-the-art results reported on two datasets. When augmented with conventionally used representations obtained from news articles, Twitter, YouTube, Facebook, and Wikipedia, prediction accuracy is found to improve by 2.5-27 macro-F1 points for the two tasks.

Enes Altinisik, Hassan Sajjad, Husrev Taha Sencar et al.

Adversarial training is widely acknowledged as the most effective defense against adversarial attacks. However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a trade-off. The goal of this work is to provide an in depth comparison of different approaches for adversarial training in language models. Specifically, we study the effect of pre-training data augmentation as well as training time input perturbations vs. embedding space perturbations on the robustness and generalization of transformer-based language models. Our findings suggest that better robustness can be achieved by pre-training data augmentation or by training with input space perturbation. However, training with embedding space perturbation significantly improves generalization. A linguistic correlation analysis of neurons of the learned models reveals that the improved generalization is due to 'more specialized' neurons. To the best of our knowledge, this is the first work to carry out a deep qualitative analysis of different methods of generating adversarial examples in adversarial training of language models.

FANAR TEAM, Ummar Abbas, Mohammad Shahmeer Ahmad et al.

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 deployment infrastructure, was designed and operated entirely at QCRI, Hamad Bin Khalifa University. Fanar 2.0 is a story of resource-constrained excellence: the effort ran on 256 NVIDIA H100 GPUs, with Arabic having only ~0.5% of web data despite 400 million native speakers. Fanar 2.0 adopts a disciplined strategy of data quality over quantity, targeted continual pre-training, and model merging to achieve substantial gains within these constraints. At the core is Fanar-27B, continually pre-trained from a Gemma-3-27B backbone on a curated corpus of 120 billion high-quality tokens across three data recipes. Despite using 8x fewer pre-training tokens than Fanar 1.0, it delivers substantial benchmark improvements: Arabic knowledge (+9.1 pts), language (+7.3 pts), dialects (+3.5 pts), and English capability (+7.6 pts). Beyond the core LLM, Fanar 2.0 introduces a rich stack of new capabilities. FanarGuard is a state-of-the-art 4B bilingual moderation filter for Arabic safety and cultural alignment. The speech family Aura gains a long-form ASR model for hours-long audio. Oryx vision family adds Arabic-aware image and video understanding alongside culturally grounded image generation. An agentic tool-calling framework enables multi-step workflows. Fanar-Sadiq utilizes a multi-agent architecture for Islamic content. Fanar-Diwan provides classical Arabic poetry generation. FanarShaheen delivers LLM-powered bilingual translation. A redesigned multi-layer orchestrator coordinates all components through intent-aware routing and defense-in-depth safety validation. Taken together, Fanar 2.0 demonstrates that sovereign, resource-constrained AI development can produce systems competitive with those built at far greater scale.

Enes Altinisik, Safa Messaoud, Husrev Taha Sencar et al.

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 paper, we identify one cause of overfitting related to current practices of generating adversarial samples from misclassified samples. To address this, we propose an alternative approach that leverages the misclassified samples to mitigate the overfitting problem. We show that our approach achieves better generalization while having comparable robustness to state-of-the-art adversarial training methods on a wide range of computer vision, natural language processing, and tabular tasks.

Faaiz Joad, Majd Hawasly, Sabri Boughorbel et al.

Prior work argues that refusal in large language models is mediated by a single activation-space direction, enabling effective steering and ablation. We show that this account is incomplete. Across eleven categories of refusal and non-compliance, including safety, incomplete or unsupported requests, anthropomorphization, and over-refusal, we find that these refusal behaviors correspond to geometrically distinct directions in activation space. Yet despite this diversity, linear steering along any refusal-related direction produces nearly identical refusal to over-refusal trade-offs, acting as a shared one-dimensional control knob. The primary effect of different directions is not whether the model refuses, but how it refuses.

Enes Altinisik, Masoomali Fatehkia, Fatih Deniz et al.

Factual hallucination remains a central challenge for large language models (LLMs). Existing mitigation approaches primarily rely on either external post-hoc verification or mapping uncertainty directly to abstention during fine-tuning, often resulting in overly conservative behavior. We propose VeriFY, a training-time framework that teaches LLMs to reason about factual uncertainty through consistency-based self-verification. VeriFY augments training with structured verification traces that guide the model to produce an initial answer, generate and answer a probing verification query, issue a consistency judgment, and then decide whether to answer or abstain. To address the risk of reinforcing hallucinated content when training on augmented traces, we introduce a stage-level loss masking approach that excludes hallucinated answer stages from the training objective while preserving supervision over verification behavior. Across multiple model families and scales, VeriFY reduces factual hallucination rates by 9.7 to 53.3 percent, with only modest reductions in recall (0.4 to 5.7 percent), and generalizes across datasets when trained on a single source. The source code, training data, and trained model checkpoints will be released upon acceptance.

Asim Ersoy, Enes Altinisik, Husrev Taha Sencar et al.

Tool calling is a critical capability that allows Large Language Models (LLMs) to interact with external systems, significantly expanding their utility. However, research and resources for tool calling are predominantly English-centric, leaving a gap in our understanding of how to enable this functionality for other languages, such as Arabic. This paper investigates three key research questions: (1) the necessity of in-language (Arabic) tool-calling data versus relying on cross-lingual transfer, (2) the effect of general-purpose instruction tuning on tool-calling performance, and (3) the value of fine-tuning on specific, high-priority tools. To address these questions, we conduct extensive experiments using base and post-trained variants of an open-weight Arabic LLM. To enable this study, we bridge the resource gap by translating and adapting two open-source tool-calling datasets into Arabic. Our findings provide crucial insights into the optimal strategies for developing robust tool-augmented agents for Arabic.

Fanar Team, Ummar Abbas, Mohammad Shahmeer Ahmad et al.

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 and Fanar Prime, two highly capable Arabic Large Language Models (LLMs) that are best in the class on well established benchmarks for similar sized models. Fanar Star is a 7B (billion) parameter model that was trained from scratch on nearly 1 trillion clean and deduplicated Arabic, English and Code tokens. Fanar Prime is a 9B parameter model continually trained on the Gemma-2 9B base model on the same 1 trillion token set. Both models are concurrently deployed and designed to address different types of prompts transparently routed through a custom-built orchestrator. The Fanar platform provides many other capabilities including a customized Islamic Retrieval Augmented Generation (RAG) system for handling religious prompts, a Recency RAG for summarizing information about current or recent events that have occurred after the pre-training data cut-off date. The platform provides additional cognitive capabilities including in-house bilingual speech recognition that supports multiple Arabic dialects, voice and image generation that is fine-tuned to better reflect regional characteristics. Finally, Fanar provides an attribution service that can be used to verify the authenticity of fact based generated content. The design, development, and implementation of Fanar was entirely undertaken at Hamad Bin Khalifa University's Qatar Computing Research Institute (QCRI) and was sponsored by Qatar's Ministry of Communications and Information Technology to enable sovereign AI technology development.

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 context. In this work, we introduce FanarGuard, a bilingual moderation filter that evaluates both safety and cultural alignment in Arabic and English. We construct a dataset of over 468K prompt and response pairs, drawn from synthetic and public datasets, scored by a panel of LLM judges on harmlessness and cultural awareness, and use it to train two filter variants. To rigorously evaluate cultural alignment, we further develop the first benchmark targeting Arabic cultural contexts, comprising over 1k norm-sensitive prompts with LLM-generated responses annotated by human raters. Results show that FanarGuard achieves stronger agreement with human annotations than inter-annotator reliability, while matching the performance of state-of-the-art filters on safety benchmarks. These findings highlight the importance of integrating cultural awareness into moderation and establish FanarGuard as a practical step toward more context-sensitive safeguards.

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 encapsulation. To this end, a joint representation of the overall file metadata is developed and used in conjunction with a two-level hierarchical classification method. At the first level, our method groups videos into metaclasses considering several abstractions that represent high-level structural properties of file metadata. This is followed by a more nuanced classification of classes that comprise each metaclass. The method is evaluated on more than 20K videos obtained by combining four public video datasets. Tests show that a balanced accuracy of 91% is achieved in correctly identifying the class of a video among 119 video classes. This corresponds to an improvement of 6.5% over the conventional approach based on video file encapsulation characteristics. Furthermore, we investigate a setting relevant to forensic file recovery operations where file metadata cannot be located or are missing but video data is partially available. By estimating a partial list of encoding parameters from coded video data, we demonstrate that an identification accuracy of 57% can be achieved in camera-model identification in the absence of any other file metadata.

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 hardware and software limitations of these devices makes them vulnerable to man-in-the-middle (MITM) attacks. Due to the use of these devices in increasingly diverse and safety-critical applications, the capability to detect MITM attacks has become more critical. To address this challenge, we propose the use of the response time behavior of a BLE device observed in relation to select read and write operations and introduce an activeMITM attack detection system that identifies changes in response time. Our measurements on several BLE devices show that theirresponse time behavior exhibits very high regularity, making it a very reliable attack indicator that cannot be concealed by an attacker. Test results show that our system can very accurately and quickly detect MITM attacks while requiring a simple learning approach.

Preslav Nakov, Husrev Taha Sencar, Jisun An et al.

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 or automatically. Thus, many researchers are shifting their attention to higher granularity, aiming to profile entire news outlets, which makes it possible to detect likely "fake news" the moment it is published, by simply checking the reliability of its source. Source factuality is also an important element of systems for automatic fact-checking and "fake news" detection, as they need to assess the reliability of the evidence they retrieve online. Political bias detection, which in the Western political landscape is about predicting left-center-right bias, is an equally important topic, which has experienced a similar shift towards profiling entire news outlets. Moreover, there is a clear connection between the two, as highly biased media are less likely to be factual; yet, the two problems have been addressed separately. In this survey, we review the state of the art on media profiling for factuality and bias, arguing for the need to model them jointly. We further discuss interesting recent advances in using different information sources and modalities, which go beyond the text of the articles the target news outlet has published. Finally, we discuss current challenges and outline future research directions.

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 goal, we compare and contrast uniqueness measures proposed for different biometric modalities. Then, we introduce a new uniqueness measure that evaluates the entropy of i-vectors while taking into account speaker level variations. Our measure operates in the discrete feature space and relies on accurate estimation of the distribution of i-vectors. Therefore, i-vectors are quantized while ensuring that both the quantized and original representations yield similar speaker verification performance. Uniqueness estimates are obtained from two newly generated datasets and the public VoxCeleb dataset. The first custom dataset contains more than one and a half million speech samples of 20,741 speakers obtained from TEDx Talks videos. The second one includes over twenty one thousand speech samples from 1,595 actors that are extracted from movie dialogues. Using this data, we analyzed how several factors, such as the number of speakers, number of samples per speaker, sample durations, and diversity of utterances affect uniqueness estimates. Most notably, we determine that the discretization of i-vectors does not cause a reduction in speaker recognition performance. Our results show that the degree of distinctiveness offered by i-vector-based representation may reach 43-70 bits considering 5-second long speech samples; however, under less constrained variations in speech, uniqueness estimates are found to reduce by around 30 bits. We also find that doubling the sample duration increases the distinctiveness of the i-vector representation by around 20 bits.

Enes Altinisik, Kasim Tasdemir, Husrev Taha Sencar

Estimating the photo-response non-uniformity (PRNU) of an imaging sensor from videos is a challenging task due to complications created by several processing steps in the camera imaging pipeline. Among these steps, video coding is one of the most disruptive to PRNU estimation because of its lossy nature. Since videos are always stored in a compressed format, the ability to cope with the disruptive effects of encoding is central to reliable attribution. In this work, by focusing on the block-based operation of widely used video coding standards, we present an improved approach to PRNU estimation that exploits this behavior. To this purpose, several PRNU weighting schemes that utilize block-level parameters, such as encoding block type, quantization strength, and rate-distortion value, are proposed and compared. Our results show that the use of the coding rate of a block serves as a better estimator for the strength of PRNU with almost three times improvement in the matching statistic at low to medium coding bitrates as compared to the basic estimation method developed for photos.

Enes Altinisik, Husrev Taha Sencar

Image stabilization performed during imaging and/or post-processing poses one of the most significant challenges to photo-response non-uniformity based source camera attribution from videos. When performed digitally, stabilization involves cropping, warping, and inpainting of video frames to eliminate unwanted camera motion. Hence, successful attribution requires the inversion of these transformations in a blind manner. To address this challenge, we introduce a source camera verification method for videos that takes into account the spatially variant nature of stabilization transformations and assumes a larger degree of freedom in their search. Our method identifies transformations at a sub-frame level, incorporates a number of constraints to validate their correctness, and offers computational flexibility in the search for the correct transformation. The method also adopts a holistic approach in countering disruptive effects of other video generation steps, such as video coding and downsizing, for more reliable attribution. Tests performed on one public and two custom datasets show that the proposed method is able to verify the source of 23-30% of all videos that underwent stronger stabilization, depending on computation load, without a significant impact on false attribution.