5 citations · 12 across the 14 of their papers we have counts for
16 papers
The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
Manish Bhatt, Sarthak Munshi, Vineeth Sai Narajala +6
We prove that no continuous, utility-preserving wrapper defense-a function that preprocesses inputs before the model sees them-can make all outputs strictly safe for a…
Adversarial Hubness Detector: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems
Idan Habler, Vineeth Sai Narajala, Stav Koren +2
Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external knowledge via vector similarity search…
From Tool Orchestration to Code Execution: A Study of MCP Design Choices
Yuval Felendler, Parth A. Gandhi, Idan Habler +2
Model Context Protocols (MCPs) provide a unified platform for agent systems to discover, select, and orchestrate tools across heterogeneous execution environments. As MCP-based sys…
Manifold of Failure: Behavioral Attraction Basins in Language Models
Sarthak Munshi, Manish Bhatt, Vineeth Sai Narajala +4
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 r…
Large Empirical Case Study: Go-Explore adapted for AI Red Team Testing
Manish Bhatt, Adrian Wood, Idan Habler +1
Production LLM agents with tool-using capabilities require security testing despite their safety training. We adapt Go-Explore to evaluate GPT-4o-mini across 28 experimental runs s…
MAIF: Enforcing AI Trust and Provenance with an Artifact-Centric Agentic Paradigm
Vineeth Sai Narajala, Manish Bhatt, Idan Habler +2
The AI trustworthiness crisis threatens to derail the artificial intelligence revolution, with regulatory barriers, security vulnerabilities, and accountability gaps preventing dep…
A2AS: Agentic AI Runtime Security and Self-Defense
Eugene Neelou, Ivan Novikov, Max Moroz +15
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates mode…
Agent Capability Negotiation and Binding Protocol (ACNBP)
Ken Huang, Akram Sheriff, Vineeth Sai Narajala +1
As multi-agent systems evolve to encompass increasingly diverse and specialized agents, the challenge of enabling effective collaboration between heterogeneous agents has become pa…
COALESCE: Economic and Security Dynamics of Skill-Based Task Outsourcing Among Team of Autonomous LLM Agents
Manish Bhatt, Ronald F. Del Rosario, Vineeth Sai Narajala +1
The meteoric rise and proliferation of autonomous Large Language Model (LLM) agents promise significant capabilities across various domains. However, their deployment is increasing…
ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control
Manish Bhatt, Vineeth Sai Narajala, Idan Habler
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. Ho…
A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control
Ken Huang, Vineeth Sai Narajala, John Yeoh +6
Traditional Identity and Access Management (IAM) systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect (OIDC), and SA…
Agent Name Service (ANS): A Universal Directory for Secure AI Agent Discovery and Interoperability
Ken Huang, Vineeth Sai Narajala, Idan Habler +1
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…
Building A Secure Agentic AI Application Leveraging A2A Protocol
Idan Habler, Ken Huang, Vineeth Sai Narajala +1
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 sec…
Enterprise-Grade Security for the Model Context Protocol (MCP): Frameworks and Mitigation Strategies
Vineeth Sai Narajala, Idan Habler
The Model Context Protocol (MCP), introduced by Anthropic, provides a standardized framework for artificial intelligence (AI) systems to interact with external data sources and too…
Securing GenAI Multi-Agent Systems Against Tool Squatting: A Zero Trust Registry-Based Approach
Vineeth Sai Narajala, Ken Huang, Idan Habler
The rise of generative AI (GenAI) multi-agent systems (MAS) necessitates standardized protocols enabling agents to discover and interact with external tools. However, these protoco…
Security Steerability is All You Need
Itay Hazan, Idan Habler, Ron Bitton +1
The adoption of Generative AI (GenAI) in applications inevitably comes with the expansion of the attack surface, combining new security threats along with the traditional ones. Con…