The paper proposes and validates a comprehensive four-layer Zero Trust security architecture designed to mitigate critical vulnerabilities in autonomous AI agents handling Protected Health Information…

The paper proposes M extsuperscript{3}Att, a knowledge-poisoning framework that injects covert misinformation into medical multimodal RAG systems using paired visual data triggers, demonstrating attac…

This paper proposes a comprehensive taxonomy (SLOT) to systematically categorize security risks, attacks, and defenses specific to Retrieval-Augmented Generation (RAG), clarifying that these risks are…

This case study systematically measures how placing anonymization at different points (dataset vs. generated answer) within the RAG pipeline affects the privacy-utility trade-off, demonstrating that p…

The paper proposes the Sentinel-Strategist architecture, an adaptive defense mechanism that selectively deploys security measures in Retrieval-Augmented Generation (RAG) systems to significantly reduc…

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss o…

The paper introduces SAMD, an automated tool that uses STPA-Sec to identify potential false data injection attack scenarios in AI/ML-enabled medical devices during the design phase.

This paper provides the first comprehensive, end-to-end survey dedicated to the security of Retrieval-Augmented Generation (RAG) systems, systematically mapping threats, defenses, and benchmarks acros…

This paper systematically measured web tracking across 20 popular AI chatbots, finding that a majority share both conversational content and user identity information with third parties.

This paper empirically evaluates the use of Retrieval-Augmented Generation (RAG) for malware explanation and finds that RAG frequently degrades explanation quality by adding noise when structured secu…

CyberCane is a neuro-symbolic framework that enhances phishing detection by combining symbolic rule analysis with privacy-preserving RAG and formal ontology reasoning, achieving high recall against AI…

The paper proposes 'Think Fast, Talk Smart,' a pipeline that separates deterministic data analysis from LLM generation, showing that offloading recurring, structured tasks to code significantly improv…

The paper introduces Factual Density (FD*), a novel retrieval signal that measures the proportion of verified facts, demonstrating that optimizing RAG retrieval based on this density significantly imp…

The paper proposes a novel, scalable technique using unique canary tokens to automatically and accurately identify which web scrapers are feeding data to specific Large Language Models (LLMs).

PIIGuard introduces a novel webpage-level defense mechanism using optimized hidden HTML fragments to prevent LLM assistants from scraping contact-style PII, achieving high defense success rates while…

The paper proposes a novel data transformation framework that creates semantically rich, privacy-preserving numeric views of EHR data, enabling large-scale research while provably breaking patient lin…

This paper analyzes the security, privacy, and ethical risks associated with OpenClaw, a locally executable AI agent system, concluding that these risks pose major barriers to its trustworthy deployme…

This paper evaluates multiple LLMs (DeepSeek-R1, OpenBioLLM-Llama3, Qwen 3.5) for generating privacy-safe, high-quality synthetic mental health reports, demonstrating their effectiveness in expanding…

RealityTest introduces a large-scale, multimodal, and multilingual benchmark using real-world human data to test how AI systems disclose their identity, finding that context and phrasing are more crit…

SilentRetrieval introduces a sophisticated, two-stage data poisoning attack that successfully hijacks Retrieval-Augmented Generation (RAG) systems by injecting adversarially crafted, yet highly fluent…