arXiv subjects

Cuneyt Gurcan Akcora

Publications and source records attributed to Cuneyt Gurcan Akcora.

At least 19 recordsLinked to original sources

arXiv2026

Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMs

Deployment of Large Language Models (LLMs) on memory-constrained edge devices relies heavily on aggressive post-training quantization. However, evaluating these models is largely based on zero-shot task accuracy, which depends solely on argmax predictions and is insensitive to changes in the underlying predictive distribution. Consequently, accuracy can exhibit unstable, non-monotonic behavior under progressive quantization, masking substantial fidelity loss relative to the BFloat16 (BF16) uncompressed base model and providing misleading deployment signals. We introduce a distribution-sensitive evaluation framework quantifying information loss in quantized LLMs as the divergence between full-vocabulary predictive distributions at the token decision boundary. We compute statistical distances, including Jensen-Shannon Divergence and Total Variation Distance, between outputs of full-precision and quantized models, enabling a fine-grained analysis of distributional shift. Using this framework, we quantify probability mass displacement and distributional drift relative to the BF16 reference, capturing predictive distribution changes not reflected in top-1 accuracy. We conduct a 120-run experimental matrix across five foundation architectures and four reasoning benchmarks under progressive quantization regimes, from uncompressed BF16 to Q2_K, providing a systematic fidelity analysis. Our results show divergence metrics generally increase under stronger quantization, complementing task accuracy with a fidelity signal. Across tested llama-cpp schemes, mixed-precision Q4_K generally yields lower divergence than uniform Q4_0 at similar memory footprints. These findings motivate distribution-aware evaluation as a practical diagnostic complement to task accuracy; they do not directly establish correctness, calibration, safety, or user-perceived quality.

cs.LG↗

arXiv2026

Edge Sparsification via Temporal Forman-Ricci Curvature for Dynamic Graph Learning

Temporal graph learning has become essential for analyzing real-world systems whose interactions continuously evolve over time, including financial transaction networks, communication systems, and online social platforms. However, learning from large-scale temporal graphs remains computationally challenging when networks are dense and rapidly changing. To address this limitation, we propose a network-curvature-inspired edge sparsification framework for dynamic graph learning. Our proposed method, TRicci, extends classical Forman-Ricci curvature to directed weighted temporal graphs by capturing structural support, temporal recency, and local interaction competition. Experiments on 9 transaction networks and 3 temporal graph benchmark datasets demonstrate that the proposed framework preserves predictive performance across multiple graph-level prediction tasks. The results show that TRicci sparsifies temporal graphs by approximately 80% while reducing end-to-end downstream training and inference time by an average of 55.94%, without substantial degradation in predictive performance. Our findings suggest that temporal curvature can serve as a principled basis for scalable temporal graph learning by preserving predictive temporal-structural information under substantial sparsification.

cs.LG↗

arXiv2026

The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

Post-Training Quantization has become widely used to compress large language models to make them deployable on resource-constrained devices. However, the evaluation of quantization methods mainly uses accuracy and perplexity, which cannot capture the behavioral changes in the quantized variants. In this work, we propose Correctness Agreement, a decision-level metric that can measure the intersection of correct predictions between the base model and its quantized variant. We use this metric across multiple models and quantization bit levels (8-bit to 2-bit), and we find that the base and quantized variants usually have a shift in behavior even when accuracy and perplexity are preserved. In order to explain this effect, we study the effect of quantization on the structure of the attention weights using statistical and distributional measures. The results reveal a breakpoint at low bit widths and show that query and key projections are more sensitive to quantization than the value and output projections. These results prove the illusion of equivalency between the base and quantized models and inspire behavioral evaluation beyond perplexity and accuracy for quantization methods.

cs.AI↗

arXiv2026

TopoFormer: Topology Meets Attention for Graph Learning

We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences. At the core of our method is Topo-Scan, a novel module that decomposes a graph into a short, ordered sequence of topological tokens by slicing over node or edge filtrations. These sequences capture multi-scale structural patterns, from local motifs to global organization, and are processed by a Transformer to produce expressive graph-level embeddings. Unlike traditional persistent homology pipelines, Topo-Scan is parallelizable, avoids costly diagram computations, and integrates seamlessly with standard deep learning architectures. We provide theoretical guarantees on the stability of our topological encodings and demonstrate state-of-the-art performance across graph classification and molecular property prediction benchmarks. Our results show that Topoformer matches or exceeds strong GNN and topology-based baselines while offering predictable and efficient compute. This work opens a new path for parallelizable and unifying approaches to graph representation learning that integrate topological inductive biases into attention frameworks.

cs.LG↗

arXiv2026

Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection

The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely on Graph Neural Networks (GNNs). However, the effectiveness of these GNN-based detectors in real-world settings remains poorly understood. In practice, attackers continuously adapt their strategies as well as must operate under domain-specific and temporal constraints, which can fundamentally limit the applicability of existing attack methods. As a result, there is a critical need for robust GNN-based bot detection methods under realistic, constraint-aware attack scenarios. To address this gap, we introduce BOCLOAK to systematically evaluate the robustness of GNN-based social bot detection via both edge editing and node injection adversarial attacks under realistic constraints. BOCLOAK constructs a probability measure over spatio-temporal neighbor features and learns an optimal transport geometry that separates human and bot behaviors. It then decodes transport plans into sparse, plausible edge edits that evade detection while obeying real-world constraints. We evaluate BOCLOAK across three social bot datasets, five state-of-the-art bot detectors, three adversarial defenses, and compare it against four leading graph adversarial attack baselines. BOCLOAK achieves up to 80.13% higher attack success rates while using 99.80% less GPU memory under realistic real-world constraints. Most importantly, BOCLOAK shows that optimal transport provides a lightweight, principled framework for bridging the gap between adversarial attacks and real-world bot detection.

cs.LG↗

arXiv2026

Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation

Adversarial learning and the robustness of Graph Neural Networks (GNNs) are topics of widespread interest in the machine learning community, as documented by the number of adversarial attacks and defenses designed for these purposes. While a rigorous evaluation of these adversarial methods is necessary to understand the robustness of GNNs in real-world applications, we posit that many works in the literature do not share the same experimental settings, leading to ambiguous and potentially contradictory scientific conclusions. In this benchmark, we demonstrate the importance of adopting fair, robust, and standardized evaluation protocols in adversarial GNN research. We perform a comprehensive re-evaluation of seven widely used attacks and eight recent defenses under both poisoning and evasion scenarios, across six popular graph datasets. Our study spans over 453,000 experiments conducted within a unified framework. We observe substantial differences in adversarial attack performance when evaluated under a fair and robust procedure. Our findings reveal that previously overlooked factors, such as target node selection and the training process of the attacked model, have a profound impact on attack effectiveness, to the extent of completely distorting performance insights. These results underscore the urgent need for standardized evaluations in adversarial graph machine learning.

cs.LG↗

arXiv2026

MoltGraph: A Longitudinal Temporal Graph Dataset of Moltbook for Coordinated-Agent Detection

Agent-native social platforms such as Moltbook are rapidly emerging, yet they inherit and amplify classical influence and abuse attacks, where coordinated agents strategically comment and upvote to manipulate visibility and propagate narratives across communities. However, rigorous measurement and learning-based monitoring remain constrained by the absence of longitudinal, graph-native datasets for agentic social networks that jointly capture heterogeneous interactions, temporal drift, and visibility signals needed to connect coordination behavior to downstream exposure. We introduce MoltGraph as a realistic longitudinal agentic social-network graph dataset for studying how agents behave, coordinate, and evolve in the wild, enabling reproducible measurement on emerging multi-agent social ecosystems. Using MoltGraph, we provide the first graph-centric characterization of Moltbook as a dynamic network: (i) heavy-tailed connectivity with power-law exponents in the range alpha in [1.86, 2.72], (ii) accelerating hub formation and attention centralization where the top 1% agents account for 29.00% of engagements, (iii) bursty, short-lived coordination episodes, 98.33% last under 24 hours, and (iv) measurable exposure effects across submolts. In matched analyses, posts receiving coordinated engagement exhibit 506.35% higher early interaction rates (within H=5 days) and 242.63% higher downstream exposure in feeds than non-coordinated controls.

cs.SI↗

arXiv2026

ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks

Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we propose a novel framework, ATEX-CF that unifies adversarial attack techniques with counterfactual explanation generation-a connection made feasible by their shared goal of flipping a node's prediction, yet differing in perturbation strategy: adversarial attacks often rely on edge additions, while counterfactual methods typically use deletions. Unlike traditional approaches that treat explanation and attack separately, our method efficiently integrates both edge additions and deletions, grounded in theory, leveraging adversarial insights to explore impactful counterfactuals. In addition, by jointly optimizing fidelity, sparsity, and plausibility under a constrained perturbation budget, our method produces instance-level explanations that are both informative and realistic. Experiments on synthetic and real-world node classification benchmarks demonstrate that ATEX-CF generates faithful, concise, and plausible explanations, highlighting the effectiveness of integrating adversarial insights into counterfactual reasoning for GNNs.

cs.LG↗

arXiv2025

TopER: Topological Embeddings in Graph Representation Learning

Graph embeddings play a critical role in graph representation learning, allowing machine learning models to explore and interpret graph-structured data. However, existing methods often rely on opaque, high-dimensional embeddings, limiting interpretability and practical visualization. In this work, we introduce Topological Evolution Rate (TopER), a novel, low-dimensional embedding approach grounded in topological data analysis. TopER simplifies a key topological approach, Persistent Homology, by calculating the evolution rate of graph substructures, resulting in intuitive and interpretable visualizations of graph data. This approach not only enhances the exploration of graph datasets but also delivers competitive performance in graph clustering and classification tasks. Our TopER-based models achieve or surpass state-of-the-art results across molecular, biological, and social network datasets in tasks such as classification, clustering, and visualization.

cs.LG↗

arXiv2025

SCNode: Spatial and Contextual Coordinates for Graph Representation Learning

Effective node representation lies at the heart of Graph Neural Networks (GNNs), as it directly impacts their ability to perform downstream tasks such as node classification and link prediction. Most existing GNNs, particularly message passing graph neural networks, rely on neighborhood aggregation to iteratively compute node embeddings. While powerful, this paradigm suffers from well-known limitations of oversquashing, oversmoothing, and underreaching that degrade representation quality. More critically, MPGNNs often assume homophily, where connected nodes share similar features or labels, leading to poor generalization in heterophilic graphs where this assumption breaks down. To address these challenges, we propose \textit{SCNode}, a \textit{Spatial-Contextual Node Embedding} framework designed to perform consistently well in both homophilic and heterophilic settings. SCNode integrates spatial and contextual information, yielding node embeddings that are not only more discriminative but also structurally aware. Our approach introduces new homophily matrices for understanding class interactions and tendencies. Extensive experiments on benchmark datasets show that SCNode achieves superior performance over conventional GNN models, demonstrating its robustness and adaptability in diverse graph structures.

cs.LG↗

arXiv2025

MiNT: Multi-Network Training for Transfer Learning on Temporal Graphs

Temporal Graph Learning (TGL) has become a robust framework for discovering patterns in dynamic networks and predicting future interactions. While existing research has largely concentrated on learning from individual networks, this study explores the potential of learning from multiple temporal networks and its ability to transfer to unobserved networks. To achieve this, we introduce Temporal Multi-network Training MiNT, a novel pre-training approach that learns from multiple temporal networks. With a novel collection of 84 temporal transaction networks, we pre-train TGL models on up to 64 networks and assess their transferability to 20 unseen networks. Remarkably, MiNT achieves state-of-the-art results in zero-shot inference, surpassing models individually trained on each network. Our findings further demonstrate that increasing the number of pre-training networks significantly improves transfer performance. This work lays the groundwork for developing Temporal Graph Foundation Models, highlighting the significant potential of multi-network pre-training in TGL.

cs.LG↗

arXiv2024

SoK: Prompt Hacking of Large Language Models

The safety and robustness of large language models (LLMs) based applications remain critical challenges in artificial intelligence. Among the key threats to these applications are prompt hacking attacks, which can significantly undermine the security and reliability of LLM-based systems. In this work, we offer a comprehensive and systematic overview of three distinct types of prompt hacking: jailbreaking, leaking, and injection, addressing the nuances that differentiate them despite their overlapping characteristics. To enhance the evaluation of LLM-based applications, we propose a novel framework that categorizes LLM responses into five distinct classes, moving beyond the traditional binary classification. This approach provides more granular insights into the AI's behavior, improving diagnostic precision and enabling more targeted enhancements to the system's safety and robustness.

cs.CR↗

arXiv2024

Data Depth and Core-based Trend Detection on Blockchain Transaction Networks

Blockchains are significantly easing trade finance, with billions of dollars worth of assets being transacted daily. However, analyzing these networks remains challenging due to the sheer volume and complexity of the data. We introduce a method named InnerCore that detects market manipulators within blockchain-based networks and offers a sentiment indicator for these networks. This is achieved through data depth-based core decomposition and centered motif discovery, ensuring scalability. InnerCore is a computationally efficient, unsupervised approach suitable for analyzing large temporal graphs. We demonstrate its effectiveness by analyzing and detecting three recent real-world incidents from our datasets: the catastrophic collapse of LunaTerra, the Proof-of-Stake switch of Ethereum, and the temporary peg loss of USDC - while also verifying our results against external ground truth. Our experiments show that InnerCore can match the qualified analysis accurately without human involvement, automating blockchain analysis in a scalable manner, while being more effective and efficient than baselines and state-of-the-art attributed change detection approach in dynamic graphs.

cs.LG↗

arXiv2024

Machine Learning for Blockchain Data Analysis: Progress and Opportunities

Blockchain technology has rapidly emerged to mainstream attention, while its publicly accessible, heterogeneous, massive-volume, and temporal data are reminiscent of the complex dynamics encountered during the last decade of big data. Unlike any prior data source, blockchain datasets encompass multiple layers of interactions across real-world entities, e.g., human users, autonomous programs, and smart contracts. Furthermore, blockchain's integration with cryptocurrencies has introduced financial aspects of unprecedented scale and complexity such as decentralized finance, stablecoins, non-fungible tokens, and central bank digital currencies. These unique characteristics present both opportunities and challenges for machine learning on blockchain data. On one hand, we examine the state-of-the-art solutions, applications, and future directions associated with leveraging machine learning for blockchain data analysis critical for the improvement of blockchain technology such as e-crime detection and trends prediction. On the other hand, we shed light on the pivotal role of blockchain by providing vast datasets and tools that can catalyze the growth of the evolving machine learning ecosystem. This paper serves as a comprehensive resource for researchers, practitioners, and policymakers, offering a roadmap for navigating this dynamic and transformative field.

cs.CR↗

arXiv2024

Explaining the Power of Topological Data Analysis in Graph Machine Learning

Topological Data Analysis (TDA) has been praised by researchers for its ability to capture intricate shapes and structures within data. TDA is considered robust in handling noisy and high-dimensional datasets, and its interpretability is believed to promote an intuitive understanding of model behavior. However, claims regarding the power and usefulness of TDA have only been partially tested in application domains where TDA-based models are compared to other graph machine learning approaches, such as graph neural networks. We meticulously test claims on TDA through a comprehensive set of experiments and validate their merits. Our results affirm TDA's robustness against outliers and its interpretability, aligning with proponents' arguments. However, we find that TDA does not significantly enhance the predictive power of existing methods in our specific experiments, while incurring significant computational costs. We investigate phenomena related to graph characteristics, such as small diameters and high clustering coefficients, to mitigate the computational expenses of TDA computations. Our results offer valuable perspectives on integrating TDA into graph machine learning tasks.

cs.LG↗

arXiv2023

Chainlet Orbits: Topological Address Embedding for the Bitcoin Blockchain

The rise of cryptocurrencies like Bitcoin, which enable transactions with a degree of pseudonymity, has led to a surge in various illicit activities, including ransomware payments and transactions on darknet markets. These illegal activities often utilize Bitcoin as the preferred payment method. However, current tools for detecting illicit behavior either rely on a few heuristics and laborious data collection processes or employ computationally inefficient graph neural network (GNN) models that are challenging to interpret. To overcome the computational and interpretability limitations of existing techniques, we introduce an effective solution called Chainlet Orbits. This approach embeds Bitcoin addresses by leveraging their topological characteristics in transactions. By employing our innovative address embedding, we investigate e-crime in Bitcoin networks by focusing on distinctive substructures that arise from illicit behavior. The results of our node classification experiments demonstrate superior performance compared to state-of-the-art methods, including both topological and GNN-based approaches. Moreover, our approach enables the use of interpretable and explainable machine learning models in as little as 15 minutes for most days on the Bitcoin transaction network.

cs.CR↗

arXiv2022

Blockchain: A Graph Primer

Bitcoin and its underlying technology, blockchain, have gained significant popularity in recent years. Satoshi Nakamoto designed Bitcoin to enable a secure, distributed platform without the need for central authorities, and blockchain has been hailed as a paradigm that will be as impactful as Big Data, Cloud Computing, and Machine Learning. Blockchain incorporates innovative ideas from various fields, such as public-key encryption and distributed systems. As a result, readers often encounter resources that explain Blockchain technology from a single perspective, leaving them with more questions than answers. In this primer, we aim to provide a comprehensive view of blockchain. We will begin with a brief history and introduce the building blocks of the blockchain. As graph mining is a major area of blockchain analysis, we will delve into the graph-theoretical aspects of Blockchain technology. We will also discuss the future of blockchain and explain how extensions such as smart contracts and decentralized autonomous organizations will function. Our goal is to provide a concise but complete description of blockchain technology that is accessible to readers with no prior expertise in the field.

cs.CY↗

arXiv2022

Reduction Algorithms for Persistence Diagrams of Networks: CoralTDA and PrunIT

Topological data analysis (TDA) delivers invaluable and complementary information on the intrinsic properties of data inaccessible to conventional methods. However, high computational costs remain the primary roadblock hindering the successful application of TDA in real-world studies, particularly with machine learning on large complex networks. Indeed, most modern networks such as citation, blockchain, and online social networks often have hundreds of thousands of vertices, making the application of existing TDA methods infeasible. We develop two new, remarkably simple but effective algorithms to compute the exact persistence diagrams of large graphs to address this major TDA limitation. First, we prove that $(k+1)$-core of a graph $\mathcal{G}$ suffices to compute its $k^{th}$ persistence diagram, $PD_k(\mathcal{G})$. Second, we introduce a pruning algorithm for graphs to compute their persistence diagrams by removing the dominated vertices. Our experiments on large networks show that our novel approach can achieve computational gains up to 95%. The developed framework provides the first bridge between the graph theory and TDA, with applications in machine learning of large complex networks. Our implementation is available at https://github.com/cakcora/PersistentHomologyWithCoralPrunit

cs.LG↗