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…

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…

This paper demonstrates that encrypted traffic metadata (packet lengths and timing) can leak a user's persona, achieving high inference accuracy across multiple modern websites.

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…

MaskClaw is an edge-side privacy arbitrator that protects sensitive data in GUI agent screenshots by combining local visual evidence, task-specific policies, and a skill-evolution mechanism.

The paper introduces LivePI, a structured, production-like benchmark that rigorously tests the vulnerability of AI agents to indirect prompt injection across multiple real-world input surfaces, reveal…

The paper introduces the PROMPT framework to systematically analyze and mitigate privacy risks in online propaganda detection pipelines, demonstrating that current widely used methods are often non-co…

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 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.

SnapGuard proposes a lightweight, multimodal method to detect prompt injection attacks in screenshot-based web agents by analyzing visual stability and contrast-polarity textual signals, achieving hig…

This paper demonstrates that visual phishing detectors can be completely bypassed by employing simple timing-based attacks that delay the rendering of key webpage elements.

This paper provides a large-scale empirical analysis of indirect prompt injections found in webpages, revealing that prompt-based interference is a widespread, persistent, and growing threat targeting…

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 'contrastive privacy,' a formal, model-agnostic, and quantitative method for evaluating the semantic success of AI-based sanitization across multiple media modalities.

The paper develops a comprehensive, GDPR-aligned item bank of 527 statements to accurately measure user preferences regarding specific regulatory protections, addressing a gap left by older privacy me…

The paper introduces Compositional Semantic Fingerprinting (CSF), a black-box method that allows IP owners to attribute fine-tuned text-to-image models to their protected lineages using only query acc…

The paper introduces WebSP-Eval, a new framework to evaluate web agents on complex website security and privacy tasks, finding that current state-of-the-art models struggle significantly with stateful…

The paper introduces IPI-proxy, an open-source intercepting proxy toolkit designed to red-team web-browsing AI agents by injecting adversarial payloads into live HTTP responses from whitelisted domain…

The paper proposes WARD, a robust and efficient defense model that secures web agents against prompt injection attacks embedded in web content, achieving high recall and low false positives even again…