ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors
The reliability of deepfake detectors frequently degrades under black-box adversarial transfer, as these models often rely on fragile, architecture-dependent forensic cues. Existing transfer attacks often lack semantic awareness and struggle to maintain effectiveness under strict no-query constraints, particularly when perturbations are transferred from convolutional surrogates to transformer-based targets. To address these limitations, this paper introduces ARMOR++, a robust multi-agent framework designed for high-transferability deepfake evasion. The framework leverages the Qwen2.5-VL Vision
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “ARMOR++: Agentic Orchestration of a Multi-Domain Primitive S” ≈ “Fosowl/agenticSeek””
- LinkedLinked via arxiv author · 85%Christos Korgialas →
“ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors”
- LinkedLinked via arxiv author · 85%Gabriel Lee Jun Rong →
“ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors”
- LinkedLinked via arxiv author · 85%Dion Jia Xu Ho →
“ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors”
- LinkedLinked via arxiv author · 85%Pai Chet Ng →
“ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors”
- LinkedLinked via arxiv author · 85%Xiaoxiao Miao →
“ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors”
- LinkedLinked via arxiv author · 85%Konstantinos N. Plataniotis →
“ARMOR++: Agentic Orchestration of a Multi-Domain Primitive Set for Transferable Attacks on Deepfake Detectors”
- PossiblePossibly related (embedding) · 47%Open-sourcing a two-stage prompt-injection detector (regex gate + quantised DeBERTa-v3 ONNX), trained partly on real attacks from a game I ran [P] →