AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.
A benchmark of facial recognition pipelines and co-usability performances of modules.Journal of Information Technologies, 17(2):95–107
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
baseline 1
other 1
citation-polarity summary
fields
cs.CV 5years
2026 5representative citing papers
SpInShield is a temporal spectral-invariant defense that decouples semantic motion from manipulatable spectral artifacts in deepfake detectors via a learnable adversary and shortcut suppression optimization.
Embedding Arithmetic performs vector operations in the embedding space of T2I models to mitigate bias at inference time, outperforming baselines on diversity while preserving coherence via a new Concept Coherence Score.
GPT-4o achieves macro F1 scores of 0.89 for politician face recognition and 0.86 for person counting in election Instagram stories, outperforming FaceNet512, RetinaFace, and Google Cloud Vision.
A dual-stream Transformer using frozen GazeLLE backbones and custom token fusion detects mutual gaze and joint attention from dual-camera recordings, outperforming CNN baselines and a multimodal LLM on caregiver-infant data.
citing papers explorer
-
AuraMask: An Extensible Pipeline for Developing Aesthetic Anti-Facial Recognition Image Filters
AuraMask produces 40 aesthetic anti-facial recognition filters that match or exceed prior adversarial effectiveness and achieve significantly higher user acceptance in a 630-person study.
-
Exposing and Mitigating Temporal Attack in Deepfake Video Detection
SpInShield is a temporal spectral-invariant defense that decouples semantic motion from manipulatable spectral artifacts in deepfake detectors via a learnable adversary and shortcut suppression optimization.
-
Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models
Embedding Arithmetic performs vector operations in the embedding space of T2I models to mitigate bias at inference time, outperforming baselines on diversity while preserving coherence via a new Concept Coherence Score.
-
Seeing Candidates at Scale: Multimodal LLMs for Visual Political Communication on Instagram
GPT-4o achieves macro F1 scores of 0.89 for politician face recognition and 0.86 for person counting in election Instagram stories, outperforming FaceNet512, RetinaFace, and Google Cloud Vision.
-
Automated Detection of Mutual Gaze and Joint Attention in Dual-Camera Settings via Dual-Stream Transformers
A dual-stream Transformer using frozen GazeLLE backbones and custom token fusion detects mutual gaze and joint attention from dual-camera recordings, outperforming CNN baselines and a multimodal LLM on caregiver-infant data.