Position: Certified Robustness Does Not (Yet) Imply Model Security
This is an incremental position paper highlighting practical limitations in AI security for researchers and practitioners.
The paper argues that certified robustness techniques, despite being promoted as solutions to adversarial examples, are not yet ready for real-world deployment due to critical gaps such as detection without distinction and unclear evaluation criteria, and it calls for the research community to address these challenges.
While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We identify critical gaps in current research, including the paradox of detection without distinction, the lack of clear criteria for practitioners to evaluate certification schemes, and the potential security risks arising from users' expectations surrounding ``guaranteed" robustness claims. These create an alignment issue between how certifications are presented and perceived, relative to their actual capabilities. This position paper is a call to arms for the certification research community, proposing concrete steps to address these fundamental challenges and advance the field toward practical applicability.