Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization
Researchers have developed new methods to attack and defend data summarization processes against adversarial perturbations. The study focuses on how altering the similarity structure of data can degrade the quality of summaries and impact downstream AI tasks. They propose a min-max optimization for generating multi-target attacks and a regularized max-min problem for robust defense, with algorithms offering theoretical guarantees. AI
IMPACT Introduces new attack vectors and defense mechanisms for trustworthy AI pipelines, potentially improving the robustness of data processing components.