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 architectural proxy (MCP) to enforce robust, reliable tool access control for LLM agents, demonstrating that this structural enforcement is necessary because prompt-based restric…

This paper introduces EXTree, a novel structure for Attribute-based Access Control (ABAC) policies that optimizes for both fast evaluation and human-understandable explanations when access is denied.

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 proposes RTS-ABAC, a novel real-time server-aided Attribute-Based Access Control mechanism designed to secure time-critical communications in substation automation systems, achieving low-lat…

The paper introduces AgentSecBench, a security evaluation framework that measures prompt injection, privacy leakage, and tool-use integrity in LLM agents by defining formal security games and testing…

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…

LLM-FACETS introduces an open-source, privacy-preserving framework designed to enable non-technical domain experts and compliance officers to audit and evaluate the transparency and accountability of…

RuleForge is an automated system that generates and validates detection rules for web vulnerabilities from structured CVE templates, significantly improving detection accuracy and reducing false posit…

The paper proposes a unified closed-loop threat taxonomy to systematically analyze and defend foundation models by explicitly framing the bidirectional security interactions between data and models.

This paper investigates how Generative AI enables scalable, hyper-realistic fraud in Chinese e-commerce by fabricating product defect evidence, proposing new defense mechanisms like verifiable materia…

The paper introduces presidio-hardened-x402, an open-source middleware that intercepts x402 payment requests to detect and redact PII and enforce spending policies before on-chain settlement.

OpenSOC-AI is a lightweight framework that uses parameter-efficient fine-tuning of a small LLM to automate threat classification and severity assessment from raw security logs, significantly improving…

The paper analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, fin…

The paper introduces GrantBox, a new security sandbox that evaluates how well LLM agents handle real-world tool privileges, finding that agents remain highly vulnerable to sophisticated attacks.

The paper introduces a novel, large-scale dataset of vulnerable code snippets linked to CAPEC and CWE, generated using advanced LLMs, to improve automatic vulnerability detection.

The paper introduces PrivacySIM, an evaluation suite that benchmarks how well LLMs can simulate individual user privacy decisions based on persona attributes, finding that while conditioning improves…

The paper evaluates two novel LLM-based systems, RADAGAS and RefleXQLi, for generating adversarial SQL injection payloads, finding that RADAGAS-GPT4o achieves a high bypass rate, particularly against…

The paper introduces a new benchmark and decomposition method, Sufficiency-Tightness Decomposition, demonstrating that current coding agents struggle to accurately infer least-privilege authorization,…

AgentGuard is an attribute-based access control framework designed to mitigate severe security risks, such as privacy leakage and system compromise, in tool-using LLM-based agents.