autonomous multi-agent systems 1black-box extraction 1defense mechanisms 1inference-time harness 1ip leakage 1llm security 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CR2026
Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems
Yu Cui, Wuli Yang, Yirui Shi +4
The paper presents Agent Harness Distillation (AHD), a method for extracting and replicating inference-time coordination mechanisms (harnesses) from autonomous multi-agent systems…
cs.CV2025
HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection
Jialei Cui, Jianwei Du, Yanzhe Li +3
The rapid evolution of face manipulation techniques poses a critical challenge for face forgery detection: cross-domain generalization. Conventional methods, which rely on simple c…