LLMs are now proposed for fraud detection, scam investigation, content moderation, and other trust-and-safety workflows. Much of the public literature still evaluates them as models, with less attention to their behavior as components in operational pipelines. This creates a practical evidence question: what would justify placing an LLM inside a live workflow with latency, cost, escalation, human-review, and adversarial-risk constraints? We address this question through a fraud-first survey of deployment evidence. We code 49 operationally relevant sources on LLM use in fraud detection, investigation support, content moderation, and cross-cutting robustness (18 fraud, 14 moderation, 17 cross-cutting), supplemented by 15 contextual references that establish the survey boundaries. These sources include systems, benchmarks, frameworks, and deployment-relevant surveys, not 49 production deployments. The main finding is an evidence imbalance. Fraud supplies the largest task-specific portion of the coded corpus. The moderation papers, however, include more explicit public evidence on latency, cost, governance, and fairness. Among the 18 fraud and investigation sources, none report clean per-decision latency, per-decision dollar cost, or calibration evidence; most report offline task performance, retrieval gains, or case-study accuracy instead. The survey contributes a role-and-evidence organizing frame, FORTE, for locating LLMs as classifiers, retrieval interfaces, explanation generators, reviewer assistants, agents, feature extractors, or escalation components. It also contributes a minimum deployment-evidence checklist covering latency budget, cost per decision, decision threshold, explanation integrity, and adversarial pressure. The resulting agenda identifies studies needed to support deployment claims for LLM-based fraud and trust-and-safety work.
Detecting fake-order fraud at scale remains a critical challenge for large online-to-offline (O2O) service platforms, as existing approaches often rely on expert-designed features, produce black-box decisions, and provide limited interpretability. To address these limitations, we propose DeepScrub, a reinforcement learning framework built upon large language models (LLMs) for fake-order fraud detection with traceable reasoning. DeepScrub introduces three innovations. First, a semantic unification module converts heterogeneous risk signals into textual descriptions that LLMs can understand. Second, continued pre-training on risk-control corpora injects domain knowledge, and task rewards jointly evaluate prediction correctness and reasoning quality. Third, the SUggest-REflect (SURE) mechanism incorporates expert feedback and model self-checking to iteratively refine reasoning paths. On a real-world fake-order fraud detection dataset, DeepScrub achieves a macro-F1 score of 85.3%, outperforming the best baseline by 2.7 percentage points. Our task-optimized 8B model further surpasses a 32B model, showing that domain adaptation can matter more than model scale in this setting. In a four-week live pilot, DeepScrub achieved 91.8% precision and 88.5% recall, improving over first-stage human reviewers by 16.6 and 38.8 percentage points. It reduced first-stage manual review workload by 94% and saved nearly one million RMB annually. These results show that DeepScrub improves fraud review accuracy, reduces first-stage review workload, and provides traceable evidence for production risk-review workflows.
Siqi You, Bingsong Xu, Zhixiang Zheng et al.· 0 citations
The Model Context Protocol (MCP) enables LLM agents to interact with external tools through metadata exchange, tool invocation, and response consumption. Existing MCP security scanners primarily reason about suspicious semantic signals rather than real execution behaviors, which can lead to unreliable risk assessment. For example, credential-like strings may simply be placeholders rather than actual leakage. This gap requires runtime evidence for execution-related risks and careful semantic analysis for risks carried in metadata or returned content. We present FlowGuard, an evidence-grounded MCP security detection system. FlowGuard combines semantic risk triage, recon-guided payload narrowing, schema-valid probe generation, evidence adjudication, and history-guided refinement. It verifies execution-related risks through runtime evidence and detects semantic risks in tool metadata and returned content. We evaluate FlowGuard on an executable benchmark containing 1,880 MCP cases across five vulnerability categories. FlowGuard achieves F1 scores of 0.879 and 0.942 on the execution-related Command Injection and File System Access categories, respectively. Compared with existing dynamic scanners, FlowGuard reduces end-to-end latency by up to 2.23x. In the real-world evaluation, FlowGuard reports 523 findings across 326 servers. These results show that evidence-grounded detection can assess both execution-related and semantic risks in MCP interactions.
Baichao An, Pei Chen, Geng Hong et al.· 0 citations
LLMs are increasingly used to analyze spreadsheets, CSV files, and other structured data, but producing a correct-looking answer is not the same as producing a trustworthy analysis. A trustworthy result should be supported by a valid path from the user question to the relevant data evidence. This requirement creates two diagnostic questions: whether an LLM can refuse to answer or ask for clarification when such a path does not exist, and whether it can preserve the correct analysis when the same evidence is expressed in different table forms. We introduce TrustDABench, a benchmark that operationalizes these questions as reliability and robustness. Starting from the evidence-path view, we derive 19 perturbation operators and instantiate them through an Agentic-LLM-based generation framework. TrustDABench contains 2,340 human-verified perturbed instances, and we evaluate eight representative LLMs. The results show substantial headroom: the best reliability result is only 24.21% average MRS, achieved by GPT-5.5, while the best robustness result still has 9.10% average ASR, achieved by Claude-Sonnet-5. The failures are systematic: models rarely detect conflicting evidence, often continue along executable but unsupported analysis paths, and remain sensitive to perturbations that change observation boundaries or cross-table relations. These findings suggest that stronger evidence-boundary recognition and representation-invariant reasoning are still needed for reliable structured-data analysis.
Boshen Shi, Yize Liu, Chen Zhao et al.· 0 citations
The increasing adoption of autonomous coding agents accelerates software development but also introduces scoped security risks within high-impact file paths that can outpace traditional human review capacity. While prior research has primarily evaluated these systems in terms of functional correctness and productivity, this paper presents a large-scale empirical study using the AIDev dataset to systematically characterize security code smells in agent-generated pull requests (PRs). Through a combination of a validated LLM-as-a-judge framework and manual qualitative analysis, we identify and classify security misconfigurations across 16,112 file changes spanning 4,022 pull requests. Our results reveal that 38.9% of agent-generated PRs contain at least one security smell, with supply chain integrity issues accounting for 82.3% of all detected security smells. Furthermore, hard-coded credentials constitute 99.6% of all critical-severity security smells. Crucially, we find that human collaborators are responsible for introducing 67.6% of genuine leaked secrets within these agent-assisted workflows, while existing automated and human review processes fail to detect 81.1% of these credentials prior to integration. These findings highlight substantial security risks in agent-assisted software development workflows and suggest a potential reduction in developer vigilance. They also underscore the urgent need for context-aware security guardrails implemented directly at the point of human-AI collaboration.
: Phishing email attacks, a predominant and evolving cyber threat, necessitate detection systems that are not only accurate but also robust, efficient, trustworthy, and explainable. While Large Language Models (LLMs) offer transformative potential for semantic analysis in many areas, their practical deployment for phishing detection requires a holistic assessment beyond peak accuracy. This paper presents an operational phishing detection system that processes raw emails using a LLM and provides understandable explanations. We compared three fine-tuned LLMs among CamemBERT-base, XLM-RoBERTa, and Mistral 7B and we evaluate their performance, generalization capabilities, computational efficiency, and explainability on multiple significant datasets. Our results demonstrate that LLMs significantly outperform character-level models, with XLM-RoBERTa and Mistral 7B achieving over 99.4% accuracy. Critically, we reveal a fundamental trade-off: while Mistral 7B achieves marginally higher accuracy, its computational cost could be prohibitive for real-time deployment. In contrast, XLM-RoBERTa provides an optimal balance, offering state-of-the-art accuracy (99.46%), superior cross-dataset generalization (95.76% on an unseen corpus), and practical inference speed. Furthermore, by integrating SHAP-based explainability with a generative LLM, we validate that model decisions align with recognizable phishing indicators, bridging the gap between high performance and operational trust. This work provides a multi-dimensional framework for evaluating phishing detection systems and demonstrates that for most real-world applications, a multilingual, efficient encoder like XLM-RoBERTa represents the most viable and trustworthy choice.
A. Piugie, Mathieu Valois, Emmanuel Giguet et al.· Proceedings of the 23rd Inte...· 0 citations
Intrusion detection research in Industrial Control Systems (ICS) heavily depends on public datasets, yet no prior work has systematically assessed whether the collective dataset corpus supports current evaluation claims. This paper addresses this gap through a meta-review of 18 studies between 2019 and 2026, from which 83 ICS, or ICS directly related, cybersecurity datasets are identified, harmonised, and characterised using a unified five-dimensional taxonomy. The taxonomy reveals that the corpus is structurally skewed: 85.5% of datasets concentrate on late-stage OT Disruption tactics, cross-stage IT/OT progression sequences are present in only 8.4% of cases, field-device evidence at Level 0 of the Purdue hierarchy is effectively absent, and operationally sourced data accounts for only 15.7% of the collection. A parallel audit of evaluation practices shows that zero report streaming evaluation, fewer than half apply disciplined train/test partitioning, and only two satisfy reproducibility requirements. Furthermore, a taxonomy-evaluation coupling analysis shows that dataset imbalances constrain the scope and feasibility of several evaluation practices. Based on these findings, we identify three structural imbalances: i) architectural shallowness, ii) progression compression, and iii) cross-domain substitution, and derive a coordinated research agenda which covers cross-stage corpus construction, temporally structured benchmarking, event-level label standards, and governance frameworks for operational data sharing.
Konstantinos E. Kampourakis, Vyron Kampourakis, Georgios Kambourakis et al.· 0 citations