The paper introduces CAIAMAR, a multi-agent reasoning framework that achieves context-aware and high-fidelity anonymization of personally identifiable information (PII) in street imagery, significantl…

The paper introduces POIROT, a novel protocol that uses the agents within a multi-agent system itself to diagnose and detect failures, demonstrating superior performance over traditional evaluation me…

The paper introduces an agentic workflow that uses large language models (LLMs) combined with structured querying and constrained tools to automate and significantly improve the accuracy of initial se…

AutoVerifier is an LLM-based agentic framework that automates the end-to-end verification of complex technical claims, enabling non-experts to generate evidence-backed intelligence assessments.

The paper proposes TRACE, a trajectory risk-aware compression method, to effectively aggregate sparse and delayed safety evidence across long agent trajectories, achieving state-of-the-art performance…

The paper proposes Safety Context Injection (SCI), an inference-time framework that prepends a structured external risk report to protect Large Reasoning Models (LRMs) against sophisticated jailbreaks…

This study investigates how industrial practitioners perceive and manage data leakage in automotive perception systems, finding that leakage control is a socio-technical coordination problem requiring…

The paper introduces SIR-Bench, a comprehensive benchmark of 794 test cases, to rigorously evaluate autonomous security incident response agents by measuring their ability to perform deep forensic inv…

The paper proposes IPEK, a context-aware trust mechanism for VANETs, which significantly improves detection of intelligent attackers by incorporating event and location severity into trust calculation…

This paper addresses the critical need for trustworthy LLMs in science by proposing a comprehensive, multi-layered defense framework and methodology to evaluate unique scientific vulnerabilities.

This paper introduces Agentic Workflow Injection (AWI), a new class of vulnerability in LLM-powered GitHub Actions, and presents TaintAWI, a novel taint-analysis tool that identifies hundreds of explo…

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant…

The paper proposes CAMP, a cross-turn privacy framework that mitigates Cumulative PII Exposure (CPE) in multi-turn LLM conversations by tracking and masking accumulated personal data across the entire…

The paper introduces the Sovereign Context Protocol (SCP), an open-source, attribution-aware data access layer designed to standardize how Large Language Models (LLMs) connect to and track usage of hu…

The paper surveys the use of LLMs for agentic NetOps and AIOps, arguing that operational reliability depends not on the model itself, but on robust surrounding machinery and workflow-centered evaluati…

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.

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models stru…

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

The paper introduces WebPII, a novel, large-scale synthetic benchmark for detecting personally identifiable information (PII) in web screenshots, and demonstrates a model (WebRedact) that significantl…

The paper proposes a privacy-preserving smart surveillance framework that uses a MobileNetV2-based classifier for violence detection and employs decentralized, threshold-based encryption for evidence…