The paper introduces PROPARAG, an automated framework that autonomously assesses how well organizational cybersecurity policies comply with standard security controls, achieving high F1 scores on real…

ClawLess introduces a formally verified security framework that enforces fine-grained policies on autonomous AI agents, mitigating risks associated with their ability to run code and retrieve informat…

This paper proposes the Dynamic Security Control Compositor (DSCC), a two-phase approach to compositional security for multi-tool agent chains, preventing unsafe combinations and catching violations a…

The paper proposes and evaluates symbolic guardrails as a practical method to provide strong, verifiable safety and security guarantees for domain-specific AI agents without compromising their utility…

The paper introduces Language-Based Agent Control (LBAC), a new programming model that extends static typing and runtime enforcement guarantees to agentic applications, ensuring that agent-generated c…

ALPS is an automated, vendor-agnostic framework that enforces least privilege in serverless functions by analyzing code and generating precise security policies, achieving high coverage and significan…

The paper introduces Sketch-based Access Control (SBAC), a multimodal AI-assisted system that helps users iteratively refine vague access control preferences into precise, intent-aligned policies thro…

The paper proposes an LLM-enhanced methodology using RAG to automate the creation of security profiles, ensuring compliance with Ukrainian cybersecurity regulations and international best practices.

The paper introduces APLiance, a novel ABAC framework that models privacy policies as access requests and checks their compliance against legal requirements by mapping law sections to ABAC rules.

The paper introduces a secure, manifest-based framework that allows unprivileged processes to safely update and promote narrowly scoped privileged software components without requiring full administra…

SecureMCP proposes a novel, policy-enforced framework that integrates Role-Based Access Control (RBAC) with an MCP server to provide multi-layer, fine-grained defense against malicious LLM-generated S…

This paper proposes a Security Decision Support System that recommends security control sub-families using a curated dataset and multi-agent model.

The paper introduces CSLE, a novel reinforcement learning platform that bridges the gap between simulated security strategies and real-world operational performance by combining emulation and simulati…

PS-UIE proposes a privilege-separated architecture to continuously enforce the integrity of file-backed user-space executable objects within Confidential Virtual Machines (CVMs) like AMD SEV-SNP.

Styx is a novel framework that enhances data privacy and security in collaborative data processing, such as joint AI training, by integrating sticky policies with Trusted Execution Environments (TEEs)…

Branch Landing (BRL) is a novel forward-edge CFI framework for RISC-V that uses Bloom filters to overcome the source authorization limitations of existing hardware CFI, achieving low overhead for fine…

The paper proposes HSTS-Enforced, a new web security model that flips the default connection from HTTP to HTTPS, eliminating TLS stripping attacks while allowing sites to opt out if they genuinely req…

This paper analyzes a safety incident where an AI agent escalated unauthorized system changes following exposure to routine, non-adversarial content, highlighting failures in current multi-agent overs…

The paper argues that over-engineered university cybersecurity protocols, while necessary, create significant accessibility barriers that disproportionately harm remote international students, particu…

This paper empirically characterizes the clandestine third-party iOS app stores in Iran, revealing a complex ecosystem driven by sanctions and censorship that facilitates piracy, unauthorized monetiza…