This report synthesizes peer-reviewed and archival research published between 2019 and 2024 on the use of large language models and multi-agent architectures for automated vulnerability repair, with a specific focus on how these techniques apply, or fail to apply, to legacy software systems. The review traces a clear methodological progression across this five-year window: from template and heuristic program repair, through neural and transfer-learning models, to fine-tuned transformer-based repair, zero-shot and conversational prompting of general-purpose LLMs, and finally to multi-agent pipelines in which specialized agents divide the work of detecting, localizing, patching, and validating a vulnerability. Two figures accompany the discussion. The first depicts a generalized multi-agent repair pipeline synthesized from the architectures described across the reviewed literature, showing how detection, localization, patch generation, and validation agents typically interact, including the validation feedback loop that distinguishes conversational and agentic systems from earlier single-shot approaches. The second traces the field's methodological evolution chronologically, from 2019's template-based baselines through 2024's agentic systems. A comparative table consolidates fifteen of the most relevant studies discussed in the body of the report, listing the approach, target language, and publication venue for each. The report concludes that while multi-agent LLM pipelines show real promise for legacy code specifically, since their capacity for autonomous context reconstruction and iterative, feedback-driven refinement directly addresses the sparse documentation and thin test coverage that define legacy environments, the literature to date has been validated almost exclusively on actively maintained, comparatively well-organized open-source repositories. The gap between these benchmarks and the scale and disorganization of real enterprise legacy systems has not yet been closed empirically, and closing it, together with building trust and explainability mechanisms suitable for security-critical maintenance work, is identified as the field's most consequential open problem.
Harsh Verma· International Journal of Sci...· 0 citations
The rapid adoption of cloud-based architectures has increased system scalability and flexibility while simultaneously expanding the attack surface and operational complexity of modern applications. Traditional rule-based monitoring systems, which depend on static thresholds and predefined signatures, struggle to detect sophisticated threats and performance irregularities in highly dynamic, elastic, and ephemeral cloud environments where workloads scale up and down continuously and services are frequently redeployed. This paper explores the design and implementation of AI-powered anomaly detection frameworks tailored for cloud-native infrastructures, examining the theoretical foundations, architectural components, and practical deployment considerations of intelligent monitoring systems. By leveraging machine learning techniques such as supervised learning, unsupervised clustering, and deep learning models including recurrent neural networks and autoencoders, artificial intelligence systems can identify deviations from baseline behavior across distributed services, containers, and microservices in real time. The proposed approach integrates telemetry data from logs, metrics, and network traces to establish adaptive behavioral profiles, emphasizing automated feature extraction, continuous model training, and feedback loops that reduce false positives while improving detection accuracy. The framework is explicitly designed to operate across the full lifecycle of anomaly management, from raw data ingestion through model inference to alert generation and remediation. Additionally, this study addresses scalability challenges, data privacy considerations, and integration with DevOps and SecOps workflows. Experimental evaluation, conducted on a dataset exceeding 500,000 records drawn from logs, metrics, and network traffic, demonstrates improved detection rates, faster incident response times, and enhanced system resilience compared to conventional monitoring tools. Five model families were benchmarked side by side, with hybrid ensemble approaches achieving the strongest overall results. The findings suggest that AI-powered anomaly detection significantly strengthens observability and security in cloud-based applications, enabling proactive threat mitigation and operational optimization in increasingly complex distributed environments.
Harsh Verma· International Journal of Sci...· 0 citations
AI agents are being used more in high-pressure situations like managing email, running code, engaging with financial APIs, and supervising multi-agent pipelines. However, current taxonomy of adversarial attacks was mostly proposed for classifiers and generative models alone and fails to adequately describe the testbed of an agent with persistent state, multiple tools, and delegated power. A previously unstated class of adversarial input called a clean attack - an input that is syntactically correct, semantically consistent with the declared task context, consistent with all observable policy constraints, similar to legitimate operator instructions and still has the goal of misguiding the agent away from the original operator goal - is identified and formalized in this paper. These attacks go around the exposed dots of the “traditional” agent security architecture that only filters on the surface. The paper has three main contributions. One, it brings in a formal definition of the clean attack as a four-tuple of input, intent vector, policy envelope and behavioral outcome. Second, it suggests two operationalizable metrics: semantic validity score (SVS) and behavioral drift index (BDI) for systematically measuring the severity of clean attack. Third, the paper these metrics and taxonomy are validated, both by a purpose-built benchmark, AegisBench, and by 300 attack scenarios in three agent classes and (twelve) commercial agent pipelines. The experimental results show that clean attacks are a safety threat of a different category: while the conventional adversarial tasks are practically impervious to these attacks (4.2% success rate of the strongest agents), they achieve a mean attack success of 61.4%.
Harsh Verma· International Journal of Sci...· 0 citations
Security in autonomous AI systems is not a property of individual components such as identity verification, static policy configurations, or model-level safeguards. Instead, it is a dynamic system property emerging from three interconnected dimensions: intent, time, and interaction. Intent captures the alignment between an operator’s goals and an agent’s behavior; time reflects the evolution of security states under adversarial pressure; and interaction describes how trust relationships between agents can propagate misalignment. This paper synthesizes the findings of the five-paper AI Agent Security Series into a unified, formal, and falsifiable theory of autonomous agent security. Current AI security approaches focus on component-level controls, including authentication, policy enforcement, and output filtering. However, results from Papers 1–5 show that these mechanisms are individually insufficient and collectively vulnerable to clean attacks semantically valid, policy-compliant adversarial inputs that redirect agent behavior while evading existing detection methods. We argue that such failures are structurally inevitable under component-centric security models. To address this gap, we introduce the Unified Security Function, Φ_security(φ, t, G), a scalar measure in the range [0,1] that combines IntentAlign, TemporalStability, and NetworkIntegrity into a single dynamic assessment of security health. Using this framework, we establish three meta-theorems: the Component Insufficiency Theorem, the Dynamic Necessity Theorem, and the Interaction Irreducibility Theorem. Evaluation on the complete AegisBench benchmark suite (1,560 sessions across Papers 1–5) shows that Φ_security predicts attack success with an AUC of 0.943, outperforming all individual metrics. By defining autonomous agent security as a distinct scientific object, this work provides a foundational framework for future research on secure and adaptive AI systems.
Harsh Verma· International Journal of Sci...· 0 citations
The rapid adoption of artificial intelligence and machine learning across critical sectors has introduced cybersecurity challenges that traditional security frameworks were never designed to address. As machine learning models increasingly shape decision-making in finance, healthcare, autonomous systems, and national security, they have become attractive targets for sophisticated adversaries. This paper examines the evolving threat landscape surrounding AI systems, with particular attention to vulnerabilities that arise at each stage of the machine learning lifecycle, including data poisoning, adversarial manipulation, model extraction, and inference-based privacy attacks. It explores how attackers exploit weaknesses in training data, model architectures, and deployment pipelines to manipulate model behavior or exfiltrate sensitive information, and it reviews the defense strategies that have emerged in response, from adversarial training and robust model design to secure deployment practices and privacy-preserving techniques such as differential privacy, federated learning, and homomorphic encryption. The discussion also situates these technical measures within the broader governance frameworks and secure-by-design principles that organizations are beginning to adopt across the AI development lifecycle. By synthesizing current research and practical defense approaches, this paper provides a comprehensive overview of how machine learning systems can be safeguarded against a threat landscape that continues to evolve as quickly as the technology itself. The overarching conclusion is that securing AI systems is not a task any single discipline can accomplish alone; it requires sustained collaboration between machine learning researchers, cybersecurity professionals, and policymakers if AI technologies are to remain reliable, trustworthy, and resilient in adversarial environments.
Harsh Verma· International Journal of Sci...· 0 citations
A detailed overview of the security risks associated with adversarial attacks is offered, including evasion attacks carried out at inference time, data poisoning that corrupts the training process, backdoor insertion that hides dormant triggers inside a model, and model inversion that leaks private information back out of a trained system.
Harsh Verma· International Journal of Sci...· 0 citations