Hassan Sajjad from Dalhousie University presented research on exploring the latent space of AI models to assess their safety and trustworthiness. He discussed use cases where analyzing latent space helps understand the robustness-generalization tradeoff in adversarial training and evaluate language comprehension. Sajjad's work aims to build better AI models and increase trust in their capabilities by looking at model internals. Why it matters: Intrinsic evaluation of model internals will become important to improving AI safety and robustness.
MBZUAI faculty Kun Zhang is researching methods to improve the reliability of generative AI, particularly in healthcare applications. Current generative AI models often act as "black boxes," making it difficult to understand why a specific result was produced. Zhang's research focuses on incorporating causal relationships into AI systems to ensure more accurate and meaningful information. Why it matters: Improving the trustworthiness of generative AI is crucial for sensitive sectors like healthcare and ensuring responsible AI deployment across the region.
This paper introduces SemDiff, a novel method for generating unrestricted adversarial examples (UAEs) by exploring the semantic latent space of diffusion models. SemDiff uses multi-attribute optimization to ensure attack success while preserving the naturalness and imperceptibility of generated UAEs. Experiments on high-resolution datasets demonstrate SemDiff's superior performance compared to state-of-the-art methods in attack success rate and imperceptibility, while also evading defenses.
The paper introduces the Unscented Autoencoder (UAE), a novel deep generative model based on the Variational Autoencoder (VAE) framework. The UAE uses the Unscented Transform (UT) for a more informative posterior representation compared to the reparameterization trick in VAEs. It replaces Kullback-Leibler (KL) divergence with the Wasserstein distribution metric and demonstrates competitive performance in Fréchet Inception Distance (FID) scores.
Dr. Xinwei Sun from Microsoft Research Asia presented research on trustworthy AI, focusing on statistical learning with theoretical guarantees. The work covers methods for sparse recovery with false-discovery rate analysis and causal inference tools for robustness and explainability. Consistency and identifiability were addressed theoretically, with applications shown in medical imaging analysis. Why it matters: The research contributes to addressing key limitations of current AI models regarding explainability, reproducibility, robustness, and fairness, which are crucial for real-world applications in sensitive fields like healthcare.