Difficulty Calibration Across Time for Membership Inference in Diffusion Models
Modern diffusion models are trained on massive datasets that often include copyrighted or private images. Membership inf
#cs.CV
共收录 217 条相关情报。
← 返回所有主题Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection
Automated detection has become the essential safeguard against realistic synthetic media, but deploying it at scale requ
CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation
With the rapid advancement of text-to-image diffusion models, increasingly realistic AI-generated content has raised ser
RePAIR: Inverting Backdoor Attacks in Semantic Segmentation
Despite significant advances in computer vision, semantic segmentation models remain vulnerable to backdoor attacks, pos
Haste Makes Waste? Towards Safe Few-Step Text-to-Image Models
While few-step distilled text-to-image models have gained traction due to their fast generation times, the speed-up impl
ORBITAL: Optimization of Robust Brain--Computer Inference Through Architecture-Aware Low-Precision Compression
Compact electroencephalography (EEG) decoders enable embedded brain--computer interfaces (BCIs), but compression can alt
Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging
Artificial intelligence (AI) shows promise for breast imaging, but limited labeled data, institutional data fragmentatio
A Category-Selective Encryption Framework for Privacy Protection of UAV Images
Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillan
From Speech Tokens to Stolen Voices: Attacker-Chosen-Text Speaker Impersonation via Representation Inversion
Speech interaction systems have gradually evolved from traditional cascaded systems that use text as intermediate inform
STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks
We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simpl
Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control
Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorl
Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content
WildFakeToolBench: Benchmarking AI-Generated Image Detectors with Web-Sourced Image Processing
As AI generated images are getting popular these days, discussions on such generations are widely existed in current pub
A Unified Evaluation Framework of Physical Adversarial Robustness in the Edge VLM Era
Recent advancements in Vision-Language Models (VLMs) enable end-to-end visual grounding via language prompts and generat
BrushOff: Stroke-Based Re-rendering as a Watermark Removal Attack on Painting
Invisible watermarks are used to mark who owns a painting. We show that a simple attack removes the most robust one we t
Defending Against Dormant Poisoning Attacks Across Language and Multimodal Agents
Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after
From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images
Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal lar
Erase the Mark, Preserve the Motion: Temporally Consistent Removal of Video Watermarks
Recent advances in video generation have increased the demand for reliable watermarking for copyright protection, yet th
An Agentic ENF Framework for Forensic Video Authentication Against Generative AI
Generative models now synthesise video that is hard to distinguish from genuine footage, and learned detectors that key
GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate