arXiv subjects

Jacques Klein

Publications and source records attributed to Jacques Klein.

At least 55 records · Page 3Linked to original sources

arXiv2025

Beyond Real Faces: Synthetic Datasets Can Achieve Reliable Recognition Performance without Privacy Compromise

The deployment of facial recognition systems has created an ethical dilemma: achieving high accuracy requires massive datasets of real faces collected without consent, leading to dataset retractions and potential legal liabilities under regulations like GDPR. While synthetic facial data presents a promising privacy-preserving alternative, the field lacks comprehensive empirical evidence of its viability. This study addresses this critical gap through extensive evaluation of synthetic facial recognition datasets. We present a systematic literature review identifying 25 synthetic facial recognition datasets (2018-2025), combined with rigorous experimental validation. Our methodology examines seven key requirements for privacy-preserving synthetic data: identity leakage prevention, intra-class variability, identity separability, dataset scale, ethical data sourcing, bias mitigation, and benchmark reliability. Through experiments involving over 10 million synthetic samples, extended by a comparison of results reported on five standard benchmarks, we provide the first comprehensive empirical assessment of synthetic data's capability to replace real datasets. Best-performing synthetic datasets (VariFace, VIGFace) achieve recognition accuracies of 95.67% and 94.91% respectively, surpassing established real datasets including CASIA-WebFace (94.70%). While those images remain private, publicly available alternatives Vec2Face (93.52%) and CemiFace (93.22%) come close behind. Our findings reveal that they ensure proper intra-class variability while maintaining identity separability. Demographic bias analysis shows that, even though synthetic data inherits limited biases, it offers unprecedented control for bias mitigation through generation parameters. These results establish synthetic facial data as a scientifically viable and ethically imperative alternative for facial recognition research.

cs.CV↗

arXiv2025

Beyond Surface Similarity: Evaluating LLM-Based Test Refactorings with Structural and Semantic Awareness

Large Language Models (LLMs) are increasingly used to refactor unit tests, improving readability and structure while preserving behavior. Evaluating such refactorings, however, remains difficult: metrics like CodeBLEU penalize beneficial renamings and edits, while semantic similarities overlook readability and modularity. We propose CTSES, a first step toward human-aligned evaluation of refactored tests. CTSES combines CodeBLEU, METEOR, and ROUGE-L into a composite score that balances semantics, lexical clarity, and structural alignment. Evaluated on 5,000+ refactorings from Defects4J and SF110 (GPT-4o and Mistral-Large), CTSES reduces false negatives and provides more interpretable signals than individual metrics. Our emerging results illustrate that CTSES offers a proof-of-concept for composite approaches, showing their promise in bridging automated metrics and developer judgments.

cs.SE↗

arXiv2025

Human-Aligned Code Readability Assessment with Large Language Models

Code readability is crucial for software comprehension and maintenance, yet difficult to assess at scale. Traditional static metrics often fail to capture the subjective, context-sensitive nature of human judgments. Large Language Models (LLMs) offer a scalable alternative, but their behavior as readability evaluators remains underexplored. We introduce CoReEval, the first large-scale benchmark for evaluating LLM-based code readability assessment, comprising over 1.4 million model-snippet-prompt evaluations across 10 state of the art LLMs. The benchmark spans 3 programming languages (Java, Python, CUDA), 2 code types (functional code and unit tests), 4 prompting strategies (ZSL, FSL, CoT, ToT), 9 decoding settings, and developer-guided prompts tailored to junior and senior personas. We compare LLM outputs against human annotations and a validated static model, analyzing numerical alignment (MAE, Pearson's, Spearman's) and justification quality (sentiment, aspect coverage, semantic clustering). Our findings show that developer-guided prompting grounded in human-defined readability dimensions improves alignment in structured contexts, enhances explanation quality, and enables lightweight personalization through persona framing. However, increased score variability highlights trade-offs between alignment, stability, and interpretability. CoReEval provides a robust foundation for prompt engineering, model alignment studies, and human in the loop evaluation, with applications in education, onboarding, and CI/CD pipelines where LLMs can serve as explainable, adaptable reviewers.

cs.SE↗

arXiv2025

SIEVE: Towards Verifiable Certification for Code-datasets

Code agents and empirical software engineering rely on public code datasets, yet these datasets lack verifiable quality guarantees. Static 'dataset cards' inform, but they are neither auditable nor do they offer statistical guarantees, making it difficult to attest to dataset quality. Teams build isolated, ad-hoc cleaning pipelines. This fragments effort and raises cost. We present SIEVE, a community-driven framework. It turns per-property checks into Confidence Cards-machine-readable, verifiable certificates with anytime-valid statistical bounds. We outline a research plan to bring SIEVE to maturity, replacing narrative cards with anytime-verifiable certification. This shift is expected to lower quality-assurance costs and increase trust in code-datasets.

cs.SE↗

arXiv2025

Reinforcement Learning-Guided Chain-of-Draft for Token-Efficient Code Generation

LLMs demonstrate surface-level fluency in code generation but struggle with structured reasoning tasks requiring correctness and semantic alignment. While Chain-of-Thought (CoT) prompting enhances reasoning through intermediate steps, it suffers from verbosity and inefficiency. Chain-of-Draft (CoD) prompting offers more concise reasoning, but the stochastic nature of LLMs produces varying solution quality, making optimal selection challenging. We propose \multicod, a reinforcement learning framework that learns to select the most promising candidate from CoD-generated solutions. Our approach uses strategy-guided prompting to encourage diverse reasoning styles and models solution selection as a contextual bandit problem. The framework optimizes interpretable features including code complexity, reasoning structure, and strategic metadata through a reward function balancing correctness, efficiency, and clarity. Experiments on MBPP, BigCodeBench, SWE-bench Verified, and Defects4J show \multicod~outperforms and in some cases, on par with standard prompting, CoT, and CoD baselines while achieving cost and token efficiency from the user's perspective through a multi-candidate design that charges only for the selected output, reducing user billing by over 50\% and improving LLM response quality, making \multicod~more sustainable and scalable for real-world deployment. Our code is available: https://anonymous.4open.science/r/MultiCoD.

cs.SE↗

arXiv2025

Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generation

Producing high-quality code across multiple programming languages is increasingly important as today's software systems are built on heterogeneous stacks. Large language models (LLMs) have advanced the state of automated programming, yet their proficiency varies sharply between languages, especially those with limited training data such as Rust, Perl, OCaml, and Erlang. Many current solutions including language-specific fine-tuning, multi-agent orchestration, transfer learning, and intermediate-representation pipelines still approach each target language in isolation, missing opportunities to share knowledge or exploit recurring cross-language patterns. XL-CoGen tackles this challenge with a coordinated multi-agent architecture that integrates intermediate representation, code generation, translation, and automated repair. Its distinguishing feature is a data-driven mechanism for selecting bridging languages: empirically derived transfer matrices identify the best intermediate languages based on demonstrated translation success rather than raw generation accuracy. The system performs early output validation, iteratively corrects errors, and reuses intermediate artifacts as contextual scaffolds for subsequent translations. Extensive experiments show that XL-CoGen yields notable improvements with 13 percentage-point gains over the strongest fine-tuned baseline and as much as 30 percentage points over existing single-language multi-agent methods. Ablation studies further demonstrate that compatibility-guided bridging significantly outperforms LLM-based heuristics, confirming the value of cumulative cross-language knowledge transfer.

cs.SE↗

arXiv2025

Security smells in infrastructure as code: a taxonomy update beyond the seven sins

Infrastructure as Code (IaC) has become essential for modern software management, yet security flaws in IaC scripts can have severe consequences, as exemplified by the recurring exploits of Cloud Web Services. Prior work has recognized the need to build a precise taxonomy of security smells in IaC scripts as a first step towards developing approaches to improve IaC security. This first effort led to the unveiling of seven sins, limited by the focus on a single IaC tool as well as by the extensive, and potentially biased, manual effort that was required. We propose, in our work, to revisit this taxonomy: first, we extend the study of IaC security smells to a more diverse dataset with scripts associated with seven popular IaC tools, including Terraform, Ansible, Chef, Puppet, Pulumi, Saltstack, and Vagrant; second, we bring in some automation for the analysis by relying on an LLM. While we leverage LLMs for initial pattern processing, all taxonomic decisions underwent systematic human validation and reconciliation with established security standards. Our study yields a comprehensive taxonomy of 62 security smell categories, significantly expanding beyond the previously known seven. We demonstrate actionability by implementing new security checking rules within linters for seven popular IaC tools, often achieving 1.00 precision score. Our evolution study of security smells in GitHub projects reveals that these issues persist for extended periods, likely due to inadequate detection and mitigation tools. This work provides IaC practitioners with insights for addressing common security smells and systematically adopting DevSecOps practices to build safer infrastructure code.

cs.CR↗

arXiv2025

Detection of security smells in IaC scripts through semantics-aware code and language processing

Infrastructure as Code (IaC) automates the provisioning and management of IT infrastructure through scripts and tools, streamlining software deployment. Prior studies have shown that IaC scripts often contain recurring security misconfigurations, and several detection and mitigation approaches have been proposed. Most of these rely on static analysis, using statistical code representations or Machine Learning (ML) classifiers to distinguish insecure configurations from safe code. In this work, we introduce a novel approach that enhances static analysis with semantic understanding by jointly leveraging natural language and code representations. Our method builds on two complementary ML models: CodeBERT, to capture semantics across code and text, and LongFormer, to represent long IaC scripts without losing contextual information. We evaluate our approach on misconfiguration datasets from two widely used IaC tools, Ansible and Puppet. To validate its effectiveness, we conduct two ablation studies (removing code text from the natural language input and truncating scripts to reduce context) and compare against four large language models (LLMs) and prior work. Results show that semantic enrichment substantially improves detection, raising precision and recall from 0.46 and 0.79 to 0.92 and 0.88 on Ansible, and from 0.55 and 0.97 to 0.87 and 0.75 on Puppet, respectively.

cs.CR↗

arXiv2025

Explainable AI for Analyzing Person-Specific Patterns in Facial Recognition Tasks

The proliferation of facial recognition systems presents major privacy risks, driving the need for effective countermeasures. Current adversarial techniques apply generalized methods rather than adapting to individual facial characteristics, limiting their effectiveness and inconspicuousness. In this work, we introduce Layer Embedding Activation Mapping (LEAM), a novel technique that identifies which facial areas contribute most to recognition at an individual level. Unlike adversarial attack methods that aim to fool recognition systems, LEAM is an explainability technique designed to understand how these systems work, providing insights that could inform future privacy protection research. We integrate LEAM with a face parser to analyze data from 1000 individuals across 9 pre-trained facial recognition models. Our analysis reveals that while different layers within facial recognition models vary significantly in their focus areas, these models generally prioritize similar facial regions across architectures when considering their overall activation patterns, which show significantly higher similarity between images of the same individual (Bhattacharyya Coefficient: 0.32-0.57) vs. different individuals (0.04-0.13), validating the existence of person-specific recognition patterns. Our results show that facial recognition models prioritize the central region of face images (with nose areas accounting for 18.9-29.7% of critical recognition regions), while still distributing attention across multiple facial fragments. Proper selection of relevant facial areas was confirmed using validation occlusions, based on just 1% of the most relevant, LEAM-identified, image pixels, which proved to be transferable across different models. Our findings establish the foundation for future individually tailored privacy protection systems centered around LEAM's choice of areas to be perturbed.

cs.CV↗

arXiv2025

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning

Within the realm of software engineering, specialized tasks on code, such as program repair, present unique challenges, necessitating fine-tuning Large language models~(LLMs) to unlock state-of-the-art performance. Fine-tuning approaches proposed in the literature for LLMs on program repair tasks generally overlook the need to reason about the logic behind code changes, beyond syntactic patterns in the data. High-performing fine-tuning experiments also usually come at very high computational costs. With MORepair, we propose a novel perspective on the learning focus of LLM fine-tuning for program repair: we not only adapt the LLM parameters to the syntactic nuances of the task of code transformation (objective 1), but we also specifically fine-tune the LLM with respect to the logical reason behind the code change in the training data (objective 2). Such a multi-objective fine-tuning will instruct LLMs to generate high-quality patches. We apply MORepair to fine-tune four open-source LLMs with different sizes and architectures. Experimental results on function-level and repository-level repair benchmarks show that the implemented fine-tuning effectively boosts LLM repair performance by 11.4% to 56.0%. We further show that our fine-tuning strategy yields superior performance compared to the state-of-the-art approaches, including standard fine-tuning, Fine-tune-CoT, and RepairLLaMA.

cs.SE↗

arXiv2025

How Small Transformation Expose the Weakness of Semantic Similarity Measures

This research examines how well different methods measure semantic similarity, which is important for various software engineering applications such as code search, API recommendations, automated code reviews, and refactoring tools. While large language models are increasingly used for these similarity assessments, questions remain about whether they truly understand semantic relationships or merely recognize surface patterns. The study tested 18 different similarity measurement approaches, including word-based methods, embedding techniques, LLM-based systems, and structure-aware algorithms. The researchers created a systematic testing framework that applies controlled changes to text and code to evaluate how well each method handles different types of semantic relationships. The results revealed significant issues with commonly used metrics. Some embedding-based methods incorrectly identified semantic opposites as similar up to 99.9 percent of the time, while certain transformer-based approaches occasionally rated opposite meanings as more similar than synonymous ones. The study found that embedding methods' poor performance often stemmed from how they calculate distances; switching from Euclidean distance to cosine similarity improved results by 24 to 66 percent. LLM-based approaches performed better at distinguishing semantic differences, producing low similarity scores (0.00 to 0.29) for genuinely different meanings, compared to embedding methods that incorrectly assigned high scores (0.82 to 0.99) to dissimilar content.

cs.CL↗

arXiv2025

Using Contrastive Learning to Improve Two-Way Reasoning in Large Language Models: The Obfuscation Task as a Case Study

This research addresses a fundamental question in AI: whether large language models truly understand concepts or simply recognize patterns. The authors propose bidirectional reasoning,the ability to apply transformations in both directions without being explicitly trained on the reverse direction, as a test for genuine understanding. They argue that true comprehension should naturally allow reversibility. For example, a model that can change a variable name like userIndex to i should also be able to infer that i represents a user index without reverse training. The researchers tested current language models and discovered what they term cognitive specialization: when models are fine-tuned on forward tasks, their performance on those tasks improves, but their ability to reason bidirectionally becomes significantly worse. To address this issue, they developed Contrastive Fine-Tuning (CFT), which trains models using three types of examples: positive examples that maintain semantic meaning, negative examples with different semantics, and forward-direction obfuscation examples. This approach aims to develop deeper understanding rather than surface-level pattern recognition and allows reverse capabilities to develop naturally without explicit reverse training. Their experiments demonstrated that CFT successfully achieved bidirectional reasoning, enabling strong reverse performance while maintaining forward task capabilities. The authors conclude that bidirectional reasoning serves both as a theoretical framework for assessing genuine understanding and as a practical training approach for developing more capable AI systems.

cs.CL↗

arXiv2025

MalLoc: Toward Fine-grained Android Malicious Payload Localization via LLMs

The rapid evolution of Android malware poses significant challenges to the maintenance and security of mobile applications (apps). Traditional detection techniques often struggle to keep pace with emerging malware variants that employ advanced tactics such as code obfuscation and dynamic behavior triggering. One major limitation of these approaches is their inability to localize malicious payloads at a fine-grained level, hindering precise understanding of malicious behavior. This gap in understanding makes the design of effective and targeted mitigation strategies difficult, leaving mobile apps vulnerable to continuously evolving threats. To address this gap, we propose MalLoc, a novel approach that leverages the code understanding capabilities of large language models (LLMs) to localize malicious payloads at a fine-grained level within Android malware. Our experimental results demonstrate the feasibility and effectiveness of using LLMs for this task, highlighting the potential of MalLoc to enhance precision and interpretability in malware analysis. This work advances beyond traditional detection and classification by enabling deeper insights into behavior-level malicious logic and opens new directions for research, including dynamic modeling of localized threats and targeted countermeasure development.

cs.CR↗

arXiv2025

Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?

Low-resource languages (LRLs) lack sufficient linguistic resources and are underrepresented in benchmark datasets, resulting in persistently lower translation quality than high-resource languages, especially in privacy-sensitive and resource-limited contexts. Firstly, this study systematically evaluates state-of-the-art smaller Large Language Models in 200 languages using the FLORES-200 benchmark, highlighting persistent deficiencies and disparities in the translation of LRLs. To mitigate these limitations, we investigate knowledge distillation from large pre-trained teacher models to Small Language Models (SLMs) through supervised fine-tuning. The results show substantial improvements; for example, the translation performance of English to Luxembourgish (EN to LB), measured by the LLM-as-a-Judge score, increases from 0.36 to 0.89 in the validation set for Llama-3.2-3B. We further investigate various fine-tuning configurations and tasks to clarify the trade-offs between data scale and training efficiency, verify that the model retains its general capabilities without significant catastrophic forgetting after training, and explore the distillation benefits to other LRLs on SLMs (Khasi, Assamese, and Ukrainian). In general, this work exposes the limitations and fairness issues of current SLMs in LRL translation and systematically explores the potential of using the distillation of knowledge from large to small models, offering practical, empirically grounded recommendations to improve LRL translation systems

cs.CL↗

arXiv2025

Rethinking Cognitive Complexity for Unit Tests: Toward a Readability-Aware Metric Grounded in Developer Perception

Automatically generated unit tests-from search-based tools like EvoSuite or LLMs-vary significantly in structure and readability. Yet most evaluations rely on metrics like Cyclomatic Complexity and Cognitive Complexity, designed for functional code rather than test code. Recent studies have shown that SonarSource's Cognitive Complexity metric assigns near-zero scores to LLM-generated tests, yet its behavior on EvoSuite-generated tests and its applicability to test-specific code structures remain unexplored. We introduce CCTR, a Test-Aware Cognitive Complexity metric tailored for unit tests. CCTR integrates structural and semantic features like assertion density, annotation roles, and test composition patterns-dimensions ignored by traditional complexity models but critical for understanding test code. We evaluate 15,750 test suites generated by EvoSuite, GPT-4o, and Mistral Large-1024 across 350 classes from Defects4J and SF110. Results show CCTR effectively discriminates between structured and fragmented test suites, producing interpretable scores that better reflect developer-perceived effort. By bridging structural analysis and test readability, CCTR provides a foundation for more reliable evaluation and improvement of generated tests. We publicly release all data, prompts, and evaluation scripts to support replication.

cs.SE↗

arXiv2025

Measuring LLM Code Generation Stability via Structural Entropy

Assessing the stability of code generation from large language models (LLMs) is essential for judging their reliability in real-world development. We extend prior "structural-entropy concepts" to the program domain by pairing entropy with abstract syntax tree (AST) analysis. For any fixed prompt, we collect the multiset of depth-bounded subtrees of AST in each generated program and treat their relative frequencies as a probability distribution. We then measure stability in two complementary ways: (i) Jensen-Shannon divergence, a symmetric, bounded indicator of structural overlap, and (ii) a Structural Cross-Entropy ratio that highlights missing high-probability patterns. Both metrics admit structural-only and token-aware variants, enabling separate views on control-flow shape and identifier-level variability. Unlike pass@k, BLEU, or CodeBLEU, our metrics are reference-free, language-agnostic, and execution-independent. We benchmark several leading LLMs on standard code generation tasks, demonstrating that AST-driven structural entropy reveals nuances in model consistency and robustness. The method runs in O(n,d) time with no external tests, providing a lightweight addition to the code-generation evaluation toolkit.

cs.SE↗

arXiv2025

ContractTrace: Retracing Smart Contract Versions for Security Analyses

Due to the inherent immutability of blockchain technology, smart contract updates require their deployment at new addresses rather than modifying existing ones, thus fragmenting version histories and creating critical blind spots for analyses. Indeed, for example, this fragmentation severely hinders security researchers ability to track vulnerability lifecycles across contract versions. While platforms like Etherscan provide detailed information about Ethereum smart contracts, they lack crucial functionality to trace predecessor-successor relationships within smart contract lineages, preventing systematic analysis of how vulnerabilities emerge, propagate, and potentially remain unresolved across versions.To address the challenge of tracing smart contract lineages, we adopt a Design Science Research (DSR) approach and introduce ContractTrace, an automated infrastructure that accurately identifies and links versions of smart contracts into coherent lineages. This tool enables the construction of lineageSet, an up-to-date, open-source dataset specifically designed to support security research on vulnerability, defect or any other property evolution patterns in smart contracts. Through a security-focused case study we demonstrate how ContractTrace reveals previously obscured vulnerability life-cycles within smart contract lineages, tracking whether critical security flaws persist or get resolved across versions. This capability is essential for understanding vulnerability propagation patterns and evaluating the effectiveness of security patches in blockchain environments. In the evaluation phase of our DSR approach, we validated our lineage detection methodology against an alternative approach using Locality-Sensitive Hashing (LSH) to cluster contract versions, confirming the security relevance and accuracy of our technique.

cs.SE↗

arXiv2025

Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning

Several closed-source LLMs have consistently outperformed open-source alternatives in program repair tasks, primarily due to their superior reasoning capabilities and extensive pre-training. This paper introduces Repairity, a novel three-stage methodology that significantly narrows this performance gap through reasoning extraction and reinforcement learning. Our approach: (1) systematically filters high-quality reasoning traces from closed-source models using correctness verification, (2) transfers this reasoning knowledge to open-source models via supervised fine-tuning, and (3) develops reinforcement learning with LLM-based feedback to further optimize performance. Empirical evaluation across multiple program repair benchmarks demonstrates that Repairity improves the performance of Qwen2.5-Coder-32B-Instruct, a base open source LLM, by 8.68\% on average, reducing the capability gap with Claude-Sonnet3.7, a state-of-the-art closed-source model, from 10.05% to 1.35%. Ablation studies confirm that both reasoning extraction and LLM-guided reinforcement learning contribute significantly to these improvements. Our methodology generalizes effectively to additional code-related tasks, enabling organizations to leverage high-quality program repair capabilities while maintaining the customizability, transparency, and deployment flexibility inherent to open-source models.

cs.SE↗