AINeutralarXiv – CS AI · Jun 116/10
🧠
Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization
Researchers propose methods to attack and defend continuous data summarization systems by exploiting vulnerabilities in similarity-based perturbations through DR-submodular optimization. The work demonstrates that adversarial attacks on upstream data processing can compromise trustworthy AI pipelines and proposes defense mechanisms with theoretical guarantees.