DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates
Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listin
#cs.CV
共收录 217 条相关情报。
← 返回所有主题No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation
Recent advances in diffusion models have enabled high-fidelity, identity-preserving image generation for personalized ap
DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization
Direct Preference Optimization (DPO) has become a widely adopted approach for aligning vision-language models (VLMs), ye
An Initial Study of Physiological Markers for Deepfake Speech Detection
Conventional deepfake speech detectors primarily target synthesis artifacts and often degrade under unseen attacks or re
SSM-Attack: Learning Where to Perturb for Black-Box Face Privacy
Face recognition systems are deployed widely enough that a photograph shared online can be matched without its subject's
Beyond User-Side Defenses: Image Protection in Open-Weight Diffusion Models
Model providers can support image protection, but open-weight deployment introduces practical constraints. We propose fo
Unsupervised Data Drift Monitoring for Deployed Deepfake Speech Detectors
Deepfake speech detectors are typically evaluated as binary classifiers on fixed benchmarks, but deployed systems face e
Not All Challenges Are Equal: Evaluating Interactive Liveness Detection Against Real-Time Face Swaps
Remote identity verification assumes that a camera stream shows a live person, yet public real-time face-swap tools can
Adversarial Robustness of Camera-Radar Sensor Fusion for Autonomous Driving
Autonomous driving (AD) relies on multi-sensor perception to interpret the surrounding environment. However, the robustn
Robust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological Imaging
Deep learning is now central to radiology, helping detect changes on X-rays, CTs, and MRIs. However, these systems are h
From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents
Audio Large Language Models (Audio LLMs) are embedded in agents for smart homes, vehicles, wearables, and embodied syste
ECGWmark: Deep Watermarking for Electrocardiogram Signals
Secure transmission of electrocardiogram (ECG) signals remains a major challenge in telecardiology. While traditional ma
LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse
Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos,
Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
Some backdoor attacks never touch an image. FLIP only changes labels: on CIFAR-10, flipping 3% of them makes a ResNet-32
WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models
Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of
Stop My Dancing! Understanding, Detecting and Attributing Motion-Aware Deepfake Videos
Pose-guided diffusion models can now synthesize entire human figures in motion, spawning a new class of deepfakes: Motio
False Claims, Credible Images: A Red-Teaming Benchmark for Commercial Image Generators
Image-generation models can now produce text-rich, natural-looking visual artifacts that are hard to distinguish from re
Visual Memory Attacks Can Persist Through The KV Cache
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images.
Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses
Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe soci
Decoy and disclosure radii of invariant shape descriptors
A recognizer that compares rotation-invariant descriptors sees a surface only up to the fiber of the descriptor. We meas