Aug 2026· International journal of computer information systems and industrial management applications· 0 citations
TL;DR
D-RELLM is presented, a defensive reverse-engineering framework for black-box security assessment of deployed LLM applications that treats the deployed application as a socio-technical system whose risk depends on instruction hierarchy, retrieval trust, authorization, tool agency, output handling, monitoring, and operational controls.
Abstract
Large language model (LLM) applications now combine hidden prompts, retrieval pipelines, memory stores, content filters, tool calls, delegated identities, and downstream automation. Security reviewers are increasingly asked to assess such systems without access to source code, model weights, prompt templates, vector-store configuration, or internal logs. This paper presents D-RELLM, a defensive reverse-engineering framework for black-box security assessment of deployed LLM applications. The framework maps observable application behavior to an attack-surface graph, executes bounded and non-destructive probes, converts evidence into reproducible risk scores, and links each finding to mitigation and re-test criteria. Unlike model-only jailbreak evaluation, D-RELLM treats the deployed application as a socio-technical system whose risk depends on instruction hierarchy, retrieval trust, authorization, tool agency, output handling, monitoring, and operational controls. The paper defines a threat model, a probe taxonomy, a weighted scoring equation, a confidence equation, an application-level aggregation method, an evidence schema, and a mitigation playbook. A synthetic pilot across three representative archetypes—chatbot, retrieval-augmented generation (RAG) assistant, and tool-using agent—illustrates how direct prompt injection, indirect prompt injection, retrieval poisoning exposure, excessive agency, output-handling weaknesses, and sensitive-information disclosure can be prioritized before and after remediation. The result is a practical, auditable, and publication-ready method for defenders who need to quantify residual LLM application risk from black-box evidence while avoiding unsafe exploitation.
Large Language Models (LLMs) are now deployed at an unprecedented scale across many critical sectors, rapidly transitioning from experimental AI tools to embedded components of production software systems. This accelerated adoption, often enabled by low-code integrations, has lowered technical barriers while simultaneously expanding the attack surface of modern applications, particularly when deployments occur without sufficient domain-specific security expertise. In many cases, security maturity has not progressed at the same pace as capability expansion, creating systemic exposure across confidentiality, integrity, and availability dimensions. To provide structured clarity amid this rapid growth, this paper presents a comparative and standards-aligned analysis of LLM security risks and defense mechanisms grounded in the OWASP GenAI Top-10 (2025). We systematically examine each vulnerability class, map representative attack patterns to primary mitigation strategies, evaluate their security property impact, and analyze practical limitations and implementation trade-offs. In addition, we introduce a severity-based assessment to prioritize risks according to operational and systemic impact, offering a quantitative perspective on defensive readiness. Our findings indicate that current mitigation strategies are predominantly reactive, concentrated at inference time, and unevenly distributed across the LLM lifecycle. Controls addressing training pipelines, supplychain dependencies, and autonomous system behaviors remain comparatively less mature and less standardized. By integrating vulnerability classification, defense mapping, severity prioritization, and trade-off analysis within a unified framework, this study provides actionable guidance for strengthening secure, resilient, and standards-driven LLM deployment in high-stakes environments.
Md Abdul Barek, Md Bajlur Rashid, A. K. I. Riad et al.· Annual International Compute...· 0 citations
Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their ability to autonomously generate secure authentication code remains uncertain. This paper evaluates the security architecture of authentication systems generated by five prominent AI coding assistants through a bi-modal assessment framework combining static code analysis and dynamic penetration testing, mapped to NIST SP 800-63B guidelines. The study examines model behavior across four prompting strategies Basic, Secure, NIST-Based, and Reprompting to reflect varying levels of developer guidance. Empirical results demonstrate that code generated from functional or generically secure prompts consistently omits critical protections, particularly concerning brute-force resistance, session management, and robust password handling. While providing explicit, single-shot NIST context significantly improves compliance, the findings reveal that this remains structurally inadequate. Instead, iterative Reprompting: forcing models into a contextual self-auditing loop is strictly required to achieve a comprehensive, defense-in-depth security architecture. Ultimately, this study proves that current AI coding assistants do not produce secure-by-default applications, dictating that enterprise deployments must transition from single-shot prompt engineering to continuous, standards-driven verification pipelines.
Ishpuneet Singh, Shreyas Mahajan, Gurjot Singh et al.· 0 citations
Large language models (LLMs) can rapidly generate web user interface (UI) code for intelligent multimedia applications, but the resulting code may contain avoidable client-side security weaknesses. This paper presents a security governance framework that combines pre-generation rule embedding, ESLint-based static analysis, structured feedback, and LLM-based repair. The framework was evaluated through a controlled pilot ablation study involving 10 multimedia UI requirements, five experimental groups, and three repeated runs, producing 150 requests. Across all groups, 132 outputs passed structural and task-specific validity checks, while 18 were recorded as generation failures rather than being treated as secure code. For the Full Framework, the matched-pair end-to-end static finding reduction rate was 95.16% (SD = 4.76 percentage points), the valid output rate was 90.00%, and the static-secure valid output rate was $\mathbf{7 6. 6 7 \%}(\mathbf{S D}=$ 11.55 percentage points). Holm-adjusted paired Wilcoxon tests showed statistically significant differences, with lower observed final finding counts for the Full Framework than for Vanilla, Prompt Only, and the variant without structured static feedback. Repair-enabled configurations increased the average runtime from approximately 51 s to 79 s. These results concern static candidate findings and output validity; they do not replace server-side controls or exhaustive dynamic security testing.
Shu-Ning Ping, Guangchi Liu· 2026 International Conferenc...· 0 citations
This work presents Language Model Security Modules (LMSM), a security framework that adapts the separation behind Linux Security Modules (LSM) to LLM serving and gives advances in interpretability and model-internal analysis a common path to runtime enforcement.
Xiucheng Zhang, Bonan Ruan, Junfeng Fang et al.· 0 citations
Compositional Attack Path Scoring (CAPS), a framework engineered to quantify end-to-end multi-hop risks in LLM architectures, establishes a rigorous benchmark for quantitative vulnerability management in complex, agentic LLM environments.
Software code logs are the primary lens for software system observability, yet they represent a significant, overlooked security blind spot. While essential for intrusion detection and tracking anomalous behavior, code logs create a security paradox since the more data we record for monitoring, the greater the degree for data exfiltration. As modern software systems scale, manual verification becomes impractical, transforming code logs into an unmanaged liability where sensitive information such as PIIs, database credentials, API and private keys is inadvertently captured. Current tools rely on brittle pattern-matching and lexical signatures, rendering them context-blind. Because they focus exclusively on the surface-level syntax, such tools miss the core and intent that define actual security risks. In this paper, we argue that such paradigms are fundamentally insufficient for modern software complexity and propose a shift from standard pattern matching models to semantic security models. By analyzing the structural and contextual layers of code logs relative to the surrounding codebase, we propose alternative strategies to treat logs as highly prioritized dimensional constructs. This approach allows for the automated detection of latent vulnerabilities that currently evade standard security controls.
Rrezarta Krasniqi, A. Shruti· SIGSOFT FSE Companion· 0 citations