y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#integrated-gradients News & Analysis

2 articles tagged with #integrated-gradients. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles
AINeutralarXiv – CS AI · Jun 236/10
🧠

Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

Researchers introduce Diffusion Integrated Gradients (DiffIG), a novel explainable AI method that uses diffusion models to generate optimized attribution paths instead of relying on fixed hand-crafted paths. The approach enables inference-time controllable feature attribution with improved explanation quality and perceptual alignment compared to existing path-based methods.

AINeutralarXiv – CS AI · Jun 106/10
🧠

What Do Deepfake Speech Detectors Actually Hear?

Researchers developed an explainability pipeline that reveals what deepfake speech detectors actually focus on when identifying synthetic audio. The study found that three leading WavLM-based detectors rely on fundamentally different cues—environmental artifacts, phoneme distortions, and spectral patterns—despite achieving similar accuracy levels, with findings validated through causal masking experiments.