ForeAgent combines a Perception-Verdict MLLM architecture with hindsight-driven self-refining via sampling-reflection-evolution to reach 82.18% accuracy on Chameleon and 93.3% mean accuracy across 16 generators on AIGCDetect-Benchmark.
Copyright protection in generative ai: A technical perspective
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Introduces AWM adaptive attack using two-stage optimization and distribution estimation to bypass audio watermark detectors with low detection rates on voice datasets.
CatShift detects training data membership in LLMs by comparing output shifts induced by fine-tuning on member versus non-member data, relying on catastrophic forgetting without requiring logit access.
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.
citing papers explorer
-
Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection
ForeAgent combines a Perception-Verdict MLLM architecture with hindsight-driven self-refining via sampling-reflection-evolution to reach 82.18% accuracy on Chameleon and 93.3% mean accuracy across 16 generators on AIGCDetect-Benchmark.
-
Learning to Evade: Adaptive Attacks on Audio Watermarking
Introduces AWM adaptive attack using two-stage optimization and distribution estimation to bypass audio watermark detectors with low detection rates on voice datasets.
-
Hey, That's My Data! Token-Only Dataset Inference in Large Language Models
CatShift detects training data membership in LLMs by comparing output shifts induced by fine-tuning on member versus non-member data, relying on catastrophic forgetting without requiring logit access.
-
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
XAttnMark is a new neural audio watermarking method using partial parameter sharing, cross-attention for message retrieval, temporal conditioning, and a psychoacoustic TF masking loss that reports state-of-the-art detection and attribution robustness.