AI Explainability Tool Has a Critical Blind Spot, Researchers Warn
Scientists have discovered that a widely-used technique for interpreting how AI models work can be manipulated through subtle data tricks, potentially undermining trust in AI-driven diagnostics and clinical decisions. The finding suggests companies and hospitals deploying these explainability tools need stronger validation protocols before relying on them for high-stakes applications.
Originaltitel: Concept Activation Vectors: A Unifying View and Adversarial Attacks
Concept Activation Vectors (CAVs) are a tool from explainable AI, offering a promising approach for understanding how human-understandable concepts are encoded in a model’s latent spaces. They are computed from hidden-layer activations of inputs belonging either to a concept class or to non-concept examples. Adopting a probabilistic perspective, the distribution of the (non-)concept inputs induces a distribution over the CAV, making it a random vector in the latent space. This enables us to derive mean and covariance for different types of CAVs, leading to a unified theoretical view. This probabilistic perspective also reveals a potential vulnerability: CAVs can strongly depend on the rather arbitrary non-concept distribution, a factor largely overlooked in prior work. We illustrate this with a simple yet effective adversarial attack, underscoring the need for a more systematic study.