GLiNER Guard (GLiGuard) introduces a unified, efficient encoder family that simultaneously performs safety classification and PII detection in a single forward pass, offering a practical, low-cost alt…

GLiGuard introduces a compact, schema-conditioned bidirectional encoder that achieves state-of-the-art performance in LLM content moderation across multiple safety dimensions while drastically reducin…

The paper introduces LLM-CEG, an extended framework that uses membership inference attack success rates and model perplexity to systematically audit and optimize the privacy-utility trade-off when fin…

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 introduces a novel guardrail orchestration layer that improves the compliance and efficiency of high-stakes multimodal document generation by scoring multiple generated candidates against we…

The paper introduces Opir, an efficient family of encoder-based multi-task guardrail models that provides competitive safety classification performance across various tasks while maintaining a signifi…

The paper proposes SubPopMark, a novel subpopulation-driven framework that injects harmless, verifiable markers into distilled datasets to prevent copyright infringement and data leakage.

DataShield proposes an efficient method to identify safety-degrading samples within benign datasets, preventing the degradation of LLM safety capabilities during fine-tuning.

DataShield proposes an efficient method to identify safety-degrading samples within benign datasets, quantifying each sample's contribution to an LLM's compliance behavior.

The paper introduces GuardPhish, a large-scale dataset and evaluation framework, demonstrating that even high-performing open-source LLMs can generate actionable phishing content despite accurate inte…

This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

The paper introduces a 'Privacy Guard' framework that simultaneously reduces operational costs and eliminates data leakage risks when using LLMs by optimizing prompts and routing queries to secure mod…

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 COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving state-of-the-art safety performance with massiv…

The paper introduces COLAGUARD, a novel guardrail model that efficiently transfers multi-step safety reasoning into a continuous latent space, achieving high safety performance with massive improvemen…

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 identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper proposes Retrieval Augmented Classification (RAC) as a robust, low-leakage method for classifying confidential documents, demonstrating that RAC outperforms supervised fine-tuning (FT) parti…

The paper introduces ActInv and PAF to systematically analyze and quantify privacy leakage from intermediate activations during split inference of LLMs, proposing PriPert for enhanced defense.

LymphNode is a novel, post-hoc access control framework that protects Deep Neural Networks (DNNs) from model extraction and inversion attacks by enforcing a default-deny policy and selectively restori…