A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper proposes a watermarking-based method to detect benchmark contamination in large language models, validated on 10B tokens with controlled contamination.
B. Chen, Gregory W. Wornell
Introduces quantization index modulation (QIM) and distortion-compensated QIM for provably good digital watermarking with optimal rate-distortion-robustness tradeoffs.
Yuntao Wang, Yanghe Pan, Miao Yan, et al.
A comprehensive survey of ChatGPT and AIGC covering working principles, security/privacy threats, watermarking solutions, and future challenges.