cnn

This paper proposes a lightweight CNN architecture to improve adversarial robustness in EEG-based brain-computer interfaces, evaluating it against adversarial attacks and showing better classification performance than existing models.

CNN sues Perplexity AI for using over 17,000 articles, videos, and images without permission to power AI-generated answers, raising fundamental questions about content ownership and economic value in the AI era.

AEyeDE is an attention-based attribution framework that uses a proxy Transformer model to extract attention maps from text and trains a lightweight CNN to distinguish human-written from AI-generated text, outperforming text-only baselines and showing robustness across settings.

CNN has sued AI search startup Perplexity for allegedly copying thousands of articles, videos, and images without permission to power its AI search engine, joining a wave of legal actions by publishers against AI companies over copyright infringement.

AttnGen is an attention-guided training framework that embeds interpretability into the optimization of deep neural networks for genomic sequence classification, achieving improved accuracy and encouraging models to focus on informative nucleotide positions.