The paper introduces AURA, an LLM-powered mask-reconstruct framework, to improve text anonymization by enhancing resistance to agentic web-search re-identification while better preserving contextual u…

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…

This paper demonstrates that retrieval-augmented in-context learning systems for document QA are vulnerable to membership inference attacks, proposing novel black-box methods that exploit query prefix…

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 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 proposes TRIP-RAG, a dynamic anonymization framework that selectively anonymizes sensitive entities in knowledge bases used for RAG, significantly improving utility while maintaining strong…

The paper proposes Information Sufficiency (IS) as a comprehensive framework for privacy-preserving LLM communication, demonstrating that free-text pseudonymization outperforms existing suppression an…

The paper introduces a Contextual Integrity (CI) framework and a new benchmark (DelegateCI-Bench) to rewrite user queries sent to cloud LLMs, ensuring only task-essential information is retained while…

This paper proposes the first web-focused threat model for agentic browsers, demonstrating that traditional web social engineering attacks can be amplified into dangerous, reproducible threats when ex…

The paper systematically evaluates eight privacy-preserving techniques for LLM requests, finding that a combination of local inference, redaction, and semantic rephrasing provides the best overall pro…

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…

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…

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 character-level differential privacy mechanism to sanitize sensitive user prompts for LLMs, achieving high privacy for PII while maintaining utility for non-sensitive context.

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

The paper proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data di…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

The paper introduces SONAR, a prompt sanitization framework that uses natural language inference metrics to identify and remove malicious instructions injected into LLM prompts, achieving near-zero at…

The paper introduces ARGUS, a defense mechanism that uses provenance-aware decision auditing to protect LLM agents from sophisticated, context-aware prompt injection attacks, significantly reducing th…