The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

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 ImageProtector, a user-side method that embeds an imperceptible perturbation into images to prevent Multi-modal Large Language Models (MLLMs) from analyzing and extracting sensiti…

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…

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…

This paper introduces TwoHamsters, a new benchmark that rigorously tests Multi-Concept Compositional Unsafety (MCCU) in text-to-image models, demonstrating that current state-of-the-art models and saf…

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 demonstrates that current AI watermark removal techniques fail to achieve true forensic stealth, as the removal process often leaves behind detectable signals that distinguish the output fro…

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 AHV-D&S, a novel training-free inference-time safeguard that detects and suppresses risky content in Diffusion Transformers (DiTs) by quantifying token sensitivity across attention…

The paper introduces a novel framework using steganographic canary files to detect and block unauthorized processing of sensitive documents by LLMs, even when the data passes through traditional secur…

The paper introduces a robust, two-part framework (HyPE and HyPS) using hyperbolic geometry to efficiently detect and sanitize malicious prompts targeting Vision-Language Models (VLMs).

The paper proposes SAFESEAL, a novel key-conditioned watermarking framework that embeds robust, provider-specific watermarks into LLM outputs with minimal semantic distortion, effectively protecting i…

The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…

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 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 demonstrates that combining outputs from multiple large language models (LLMs) effectively cancels out statistical watermarks, revealing a fundamental vulnerability in current AI text detect…

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…

FedAttr introduces a novel client-level attribution protocol for Federated Learning (FL) that accurately identifies which clients trained on watermarked data while maintaining strong privacy guarantee…

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…