The paper proposes FedSAP, a framework that stabilizes federated prototype learning by delaying global alignment and enforcing inter-class structure, significantly improving representation quality und…

The paper introduces a novel, transferable learned attack (LT-MIA) that detects a universal 'signature of memorization' in language models, achieving high accuracy across diverse model architectures (…

The paper introduces MLLM-Microscope, a system that analyzes the internal structure of multimodal large language models (MLLMs), finding that modality fusion significantly impacts the linearity and di…

The paper introduces CrossMPI, a novel cross-modal prompt injection attack that uses image-only perturbations to steer the interpretation of both textual and visual inputs in Large Vision-Language Mod…

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…

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 FedMChain, a novel federated learning framework that structures multimodal training into sequential phases to mitigate modality competition and improve model performance while reduc…

The paper proposes MMGuard, a proactive defense mechanism that injects unlearnable, human-imperceptible perturbations into multimodal data to prevent unauthorized fine-tuning of Large Vision-Language…

The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint…

This paper analyzes label inference attacks in Vertical Federated Learning (VFL), demonstrating that existing attacks rely on feature-label distribution alignment, and proposes a zero-overhead defense…

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

The paper proposes using Maximum Independent Set (MIS) algorithms on similarity graphs to select a maximally diverse and non-redundant subset of prompts for LLM benchmarking, achieving consistent rank…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper proposes DLLM-VSR, a novel Diffusion Large Language Model framework for Visual Speech Recognition, achieving state-of-the-art performance by treating transcription as iterative masked denois…

FedTrident proposes a comprehensive framework to defend Federated Learning-based Road Condition Classification against Targeted Label-Flipping Attacks, achieving robust performance comparable to non-a…

The paper demonstrates that clinical vision-language models (VLMs) pose a significant privacy risk by allowing de-identified images to be re-linked to original reports, and proposes a targeted differe…

The paper proposes EAGLE, a novel evidence-aligned multi-agent framework, demonstrating that requiring shared visual evidence among agents is crucial for achieving reliable and trustworthy consensus i…