Vineeth Sai Narajala

Idan Habler, Vineeth Sai Narajala, Stav Koren et al.

Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external knowledge via vector similarity search. Nevertheless, these systems encounter a significant security flaw: hubness - items that frequently appear in the top-k retrieval results for a disproportionately high number of varied queries. These hubs can be exploited to introduce harmful content, alter search rankings, bypass content filtering, and decrease system performance. We introduce hubscan, an open-source security scanner that evaluates vector indices and embeddings to identify hubs in RAG systems. Hubscan presents a multi-detector architecture that integrates: (1) robust statistical hubness detection utilizing median/MAD-based z-scores, (2) cluster spread analysis to assess cross-cluster retrieval patterns, (3) stability testing under query perturbations, and (4) domain-aware and modality-aware detection for category-specific and cross-modal attacks. Our solution accommodates several vector databases (FAISS, Pinecone, Qdrant, Weaviate) and offers versatile retrieval techniques, including vector similarity, hybrid search, and lexical matching with reranking capabilities. We evaluate hubscan on Food-101, MS-COCO, and FiQA adversarial hubness benchmarks constructed using state-of-the-art gradient-optimized and centroid-based hub generation methods. hubscan achieves 90% recall at a 0.2% alert budget and 100% recall at 0.4%, with adversarial hubs ranking above the 99.8th percentile. Domain-scoped scanning recovers 100% of targeted attacks that evade global detection. Production validation on 1M real web documents from MS MARCO demonstrates significant score separation between clean documents and adversarial content. Our work provides a practical, extensible framework for detecting hubness threats in production RAG systems.

Hammad Atta, Ken Huang, Kyriakos Rock Lambros et al.

Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control Injection (LPCI) - for which no automated red-teaming instrument existed. We present LAAF (Logic-layer Automated Attack Framework), the first automated red-teaming framework to combine an LPCI-specific technique taxonomy with stage-sequential seed escalation - two capabilities absent from existing tools: Garak lacks memory-persistence and cross-session triggering; PyRIT supports multi-turn testing but treats turns independently, without seeding each stage from the prior breakthrough. LAAF provides: (i) a 49-technique taxonomy spanning six attack categories (Encoding~11, Structural~8, Semantic~8, Layered~5, Trigger~12, Exfiltration~5; see Table 1), combinable across 5 variants per technique and 6 lifecycle stages, yielding a theoretical maximum of 2,822,400 unique payloads ($49 \times 5 \times 1{,}920 \times 6$; SHA-256 deduplicated at generation time); and (ii) a Persistent Stage Breaker (PSB) that drives payload mutation stage-by-stage: on each breakthrough, the PSB seeds the next stage with a mutated form of the winning payload, mirroring real adversarial escalation. Evaluation on five production LLM platforms across three independent runs demonstrates that LAAF achieves higher stage-breakthrough efficiency than single-technique random testing, with a mean aggregate breakthrough rate of 84\% (range 83--86\%) and platform-level rates stable within 17 percentage points across runs. Layered combinations and semantic reframing are the highest-effectiveness technique categories, with layered payloads outperforming encoding on well-defended platforms.

Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala et al.

While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehensive understanding of AI safety requires characterizing the unsafe regions themselves. This paper introduces a framework for systematically mapping the Manifold of Failure in Large Language Models (LLMs). We reframe the search for vulnerabilities as a quality diversity problem, using MAP-Elites to illuminate the continuous topology of these failure regions, which we term behavioral attraction basins. Our quality metric, Alignment Deviation, guides the search towards areas where the model's behavior diverges most from its intended alignment. Across three LLMs: Llama-3-8B, GPT-OSS-20B, and GPT-5-Mini, we show that MAP-Elites achieves up to 63% behavioral coverage, discovers up to 370 distinct vulnerability niches, and reveals dramatically different model-specific topological signatures: Llama-3-8B exhibits a near-universal vulnerability plateau (mean Alignment Deviation 0.93), GPT-OSS-20B shows a fragmented landscape with spatially concentrated basins (mean 0.73), and GPT-5-Mini demonstrates strong robustness with a ceiling at 0.50. Our approach produces interpretable, global maps of each model's safety landscape that no existing attack method (GCG, PAIR, or TAP) can provide, shifting the paradigm from finding discrete failures to understanding their underlying structure.

Manish Bhatt, Sarthak Munshi, Vineeth Sai Narajala et al.

We prove that no continuous, utility-preserving wrapper defense-a function $D: X\to X$ that preprocesses inputs before the model sees them-can make all outputs strictly safe for a language model with connected prompt space, and we characterize exactly where every such defense must fail. We establish three results under successively stronger hypotheses: boundary fixation-the defense must leave some threshold-level inputs unchanged; an $ε$-robust constraint-under Lipschitz regularity, a positive-measure band around fixed boundary points remains near-threshold; and a persistent unsafe region under a transversality condition, a positive-measure subset of inputs remains strictly unsafe. These constitute a defense trilemma: continuity, utility preservation, and completeness cannot coexist. We prove parallel discrete results requiring no topology, and extend to multi-turn interactions, stochastic defenses, and capacity-parity settings. The results do not preclude training-time alignment, architectural changes, or defenses that sacrifice utility. The full theory is mechanically verified in Lean 4 and validated empirically on three LLMs.

Idan Habler, Ken Huang, Vineeth Sai Narajala et al. · amazon-science

As Agentic AI systems evolve from basic workflows to complex multi agent collaboration, robust protocols such as Google's Agent2Agent (A2A) become essential enablers. To foster secure adoption and ensure the reliability of these complex interactions, understanding the secure implementation of A2A is essential. This paper addresses this goal by providing a comprehensive security analysis centered on the A2A protocol. We examine its fundamental elements and operational dynamics, situating it within the framework of agent communication development. Utilizing the MAESTRO framework, specifically designed for AI risks, we apply proactive threat modeling to assess potential security issues in A2A deployments, focusing on aspects such as Agent Card management, task execution integrity, and authentication methodologies. Based on these insights, we recommend practical secure development methodologies and architectural best practices designed to build resilient and effective A2A systems. Our analysis also explores how the synergy between A2A and the Model Context Protocol (MCP) can further enhance secure interoperability. This paper equips developers and architects with the knowledge and practical guidance needed to confidently leverage the A2A protocol for building robust and secure next generation agentic applications.

Vineeth Sai Narajala, Idan Habler · amazon-science

The Model Context Protocol (MCP), introduced by Anthropic, provides a standardized framework for artificial intelligence (AI) systems to interact with external data sources and tools in real-time. While MCP offers significant advantages for AI integration and capability extension, it introduces novel security challenges that demand rigorous analysis and mitigation. This paper builds upon foundational research into MCP architecture and preliminary security assessments to deliver enterprise-grade mitigation frameworks and detailed technical implementation strategies. Through systematic threat modeling and analysis of MCP implementations and analysis of potential attack vectors, including sophisticated threats like tool poisoning, we present actionable security patterns tailored for MCP implementers and adopters. The primary contribution of this research lies in translating theoretical security concerns into a practical, implementable framework with actionable controls, thereby providing essential guidance for the secure enterprise adoption and governance of integrated AI systems.

Vineeth Sai Narajala, Ken Huang, Idan Habler · amazon-science

The rise of generative AI (GenAI) multi-agent systems (MAS) necessitates standardized protocols enabling agents to discover and interact with external tools. However, these protocols introduce new security challenges, particularly; tool squatting; the deceptive registration or representation of tools. This paper analyzes tool squatting threats within the context of emerging interoperability standards, such as Model Context Protocol (MCP) or seamless communication between agents protocols. It introduces a comprehensive Tool Registry system designed to mitigate these risks. We propose a security-focused architecture featuring admin-controlled registration, centralized tool discovery, fine grained access policies enforced via dedicated Agent and Tool Registry services, a dynamic trust scoring mechanism based on tool versioning and known vulnerabilities, and just in time credential provisioning. Based on its design principles, the proposed registry framework aims to effectively prevent common tool squatting vectors while preserving the flexibility and power of multi-agent systems. This work addresses a critical security gap in the rapidly evolving GenAI ecosystem and provides a foundation for secure tool integration in production environments.

Vineeth Sai Narajala, Om Narayan · amazon-science

As generative AI (GenAI) agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act, often with minimal human oversight. This paper introduces a comprehensive threat model tailored specifically for GenAI agents, focusing on how their autonomy, persistent memory access, complex reasoning, and tool integration create novel risks. This research work identifies 9 primary threats and organizes them across five key domains: cognitive architecture vulnerabilities, temporal persistence threats, operational execution vulnerabilities, trust boundary violations, and governance circumvention. These threats are not just theoretical they bring practical challenges such as delayed exploitability, cross-system propagation, cross system lateral movement, and subtle goal misalignments that are hard to detect with existing frameworks and standard approaches. To help address this, the research work present two complementary frameworks: ATFAA - Advanced Threat Framework for Autonomous AI Agents, which organizes agent-specific risks, and SHIELD, a framework proposing practical mitigation strategies designed to reduce enterprise exposure. While this work builds on existing work in LLM and AI security, the focus is squarely on what makes agents different and why those differences matter. Ultimately, this research argues that GenAI agents require a new lens for security. If we fail to adapt our threat models and defenses to account for their unique architecture and behavior, we risk turning a powerful new tool into a serious enterprise liability.

Ken Huang, Vineeth Sai Narajala, Idan Habler et al. · amazon-science

The proliferation of AI agents requires robust mechanisms for secure discovery. This paper introduces the Agent Name Service (ANS), a novel architecture based on DNS addressing the lack of a public agent discovery framework. ANS provides a protocol-agnostic registry infrastructure that leverages Public Key Infrastructure (PKI) certificates for verifiable agent identity and trust. The architecture features several key innovations: a formalized agent registration and renewal mechanism for lifecycle management; DNS-inspired naming conventions with capability-aware resolution; a modular Protocol Adapter Layer supporting diverse communication standards (A2A, MCP, ACP etc.); and precisely defined algorithms for secure resolution. We implement structured communication using JSON Schema and conduct a comprehensive threat analysis of our proposal. The result is a foundational directory service addressing the core challenges of secured discovery and interaction in multi-agent systems, paving the way for future interoperable, trustworthy, and scalable agent ecosystems.

Manish Bhatt, Vineeth Sai Narajala, Idan Habler · amazon-science

The Model Context Protocol (MCP) plays a crucial role in extending the capabilities of Large Language Models (LLMs) by enabling integration with external tools and data sources. However, the standard MCP specification presents significant security vulnerabilities, notably Tool Poisoning and Rug Pull attacks. This paper introduces the Enhanced Tool Definition Interface (ETDI), a security extension designed to fortify MCP. ETDI incorporates cryptographic identity verification, immutable versioned tool definitions, and explicit permission management, often leveraging OAuth 2.0. We further propose extending MCP with fine-grained, policy-based access control, where tool capabilities are dynamically evaluated against explicit policies using a dedicated policy engine, considering runtime context beyond static OAuth scopes. This layered approach aims to establish a more secure, trustworthy, and controllable ecosystem for AI applications interacting with LLMs and external tools.

Ken Huang, Akram Sheriff, Vineeth Sai Narajala et al. · amazon-science

As multi-agent systems evolve to encompass increasingly diverse and specialized agents, the challenge of enabling effective collaboration between heterogeneous agents has become paramount, with traditional agent communication protocols often assuming homogeneous environments or predefined interaction patterns that limit their applicability in dynamic, open-world scenarios. This paper presents the Agent Capability Negotiation and Binding Protocol (ACNBP), a novel framework designed to facilitate secure, efficient, and verifiable interactions between agents in heterogeneous multi-agent systems through integration with an Agent Name Service (ANS) infrastructure that provides comprehensive discovery, negotiation, and binding mechanisms. The protocol introduces a structured 10-step process encompassing capability discovery, candidate pre-screening and selection, secure negotiation phases, and binding commitment with built-in security measures including digital signatures, capability attestation, and comprehensive threat mitigation strategies, while a key innovation of ACNBP is its protocolExtension mechanism that enables backward-compatible protocol evolution and supports diverse agent architectures while maintaining security and interoperability. We demonstrate ACNBP's effectiveness through a comprehensive security analysis using the MAESTRO threat modeling framework, practical implementation considerations, and a detailed example showcasing the protocol's application in a document translation scenario, with the protocol addressing critical challenges in agent autonomy, capability verification, secure communication, and scalable agent ecosystem management.

Manish Bhatt, Ronald F. Del Rosario, Vineeth Sai Narajala et al. · amazon-science

The meteoric rise and proliferation of autonomous Large Language Model (LLM) agents promise significant capabilities across various domains. However, their deployment is increasingly constrained by substantial computational demands, specifically for Graphics Processing Unit (GPU) resources. This paper addresses the critical problem of optimizing resource utilization in LLM agent systems. We introduce COALESCE (Cost-Optimized and Secure Agent Labour Exchange via Skill-based Competence Estimation), a novel framework designed to enable autonomous LLM agents to dynamically outsource specific subtasks to specialized, cost-effective third-party LLM agents. The framework integrates mechanisms for hybrid skill representation, dynamic skill discovery, automated task decomposition, a unified cost model comparing internal execution costs against external outsourcing prices, simplified market-based decision-making algorithms, and a standardized communication protocol between LLM agents. Comprehensive validation through 239 theoretical simulations demonstrates 41.8\% cost reduction potential, while large-scale empirical validation across 240 real LLM tasks confirms 20.3\% cost reduction with proper epsilon-greedy exploration, establishing both theoretical viability and practical effectiveness. The emergence of proposed open standards like Google's Agent2Agent (A2A) protocol further underscores the need for frameworks like COALESCE that can leverage such standards for efficient agent interaction. By facilitating a dynamic market for agent capabilities, potentially utilizing protocols like A2A for communication, COALESCE aims to significantly reduce operational costs, enhance system scalability, and foster the emergence of specialized agent economies, making complex LLM agent functionalities more accessible and economically viable.