The paper introduces FP-Agent, a classifier that demonstrates that while browser fingerprints are poor discriminators for AI browsing agents, behavioral fingerprints (like typing and scrolling pattern…

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…

PrismWF introduces a multi-granularity patch-based Transformer to significantly improve website fingerprinting attacks by effectively modeling complex, mixed-traffic patterns from multi-tab browsing s…

This paper demonstrates that an agent's behavioral patterns, captured through passive UI interaction traces, are sufficient to identify the underlying LLM model with high accuracy, posing a significan…

The paper proposes SATA, a semantics-aware traffic augmentation framework, to significantly improve the generalization of website fingerprinting models by addressing variability in resource compositio…

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…

DEMUX is a novel framework that addresses the challenge of multi-tab website fingerprinting by treating the interleaved traffic as a demixing problem, achieving state-of-the-art performance in complex…

The paper introduces MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current…

The paper proposes Trajectory Induced Preference Optimization (TIPO) to improve mobile GUI agent personalization by explicitly modeling and optimizing for privacy-related behavioral differences in exe…

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 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…

BodhiPromptShield is a policy-aware framework that mediates prompt privacy by detecting sensitive data and replacing it with secure placeholders across multiple stages (retrieval, memory, tools) to pr…

The paper introduces Narriva, a method that generates text-based synthetic privacy personas grounded in past user behavior to accurately and efficiently simulate individual and population-level privac…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-l…

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…

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 study quantifies the privacy risk of inferring sensitive personality traits from user interactions with LLM-based conversational agents, demonstrating that machine learning models can accurately…

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 MyPhoneBench, a new framework that demonstrates that current phone-use agents often fail to respect user privacy, even when successfully completing simple tasks, primarily due to…