This paper systematically revisits and expands the threat model for backdoor attacks on semantic segmentation, proposing a unified framework (BADSEG) that demonstrates severe, previously overlooked vu…

This paper introduces a novel Vision Transformer (ViT)-based method for privacy-preserving clothing classification that accurately estimates clothing insulation for secure occupant-centric control sys…

The paper proposes a multi-ciphertext privacy-preserving framework to efficiently compute high-resolution image gradients using Fully Homomorphic Encryption (FHE) by dividing the large image into smal…

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 shows that using random cropping, a standard data augmentation technique, can naturally amplify differential privacy guarantees for machine learning models without requiring any changes to t…

The paper introduces a theoretically grounded evaluation framework for watermarking generative models, proposing a novel method (SSB) that allows for systematic design across all security-robustness-f…

The paper proposes Energy-Aware NECO, a single-pass hybrid detector that combines geometric ratio and logit-based energy scores to achieve superior pixel-wise out-of-distribution detection for semanti…

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 proposes a scalable, privacy-preserving framework for iris recognition using Fully Homomorphic Encryption (FHE), achieving accuracy comparable to cleartext while identifying the computationa…

This paper develops optimized algorithms and a pipeline architecture for high-throughput, memory-efficient batch processing of encrypted neural network inference, significantly improving performance o…

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 addresses the vulnerability of DNNs used in robotic semantic segmentation to adversarial attacks by proposing specialized detection strategies to enhance safety in robotic perception system…

The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

DP-SAPF introduces a saliency-aware parameter fine-tuning method that selectively identifies the most critical parameters for LoRA training, significantly improving the utility and fidelity of differe…

The paper proposes FLRSP, a privacy-preserving federated learning method that enhances robustness by randomly selecting model parameters for global model updates, maintaining high accuracy against sta…

The paper proposes a privacy-preserving system for crowd monitoring that counts individuals across different locations and time periods using face recognition without ever revealing personal identitie…

This paper introduces CoLA, a framework demonstrating that subset training, while efficient, introduces new and potentially greater privacy risks by leaking information about both data membership and…

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 proposes PUSNet-MK, an extension to PUSNet that enables secure multi-user, multi-key image steganography by introducing a mismatched-key isolation loss to prevent cross-key decoding.

The paper proposes CFE-PPAR, the first compression-friendly encryption method for privacy-preserving action recognition, allowing video transformers to recognize actions directly from compressed, encr…