Z. Berkay Celik

The paper introduces MIRAGE, a framework that systematically discovers semantic attacks on online HD map construction by finding plausible environmental variations that bypass standard adversarial defenses, demonstrating attacks that remove or inject critical road boundaries.

The paper introduces RoboJailBench, the first standardized evaluation framework for assessing adversarial jailbreak attacks and defenses in embodied AI systems like robots.

The paper proposes a novel pre-model safeguard that uses small draft models (SLMs) to predict the safety of prompts, significantly reducing false-negative rates while maintaining low computational overhead.

Researchers investigated the impact of cognitive heuristics on Large Language Models in code vulnerability detection, finding all models susceptible with highest susceptibility to framing.