Montasir Shams
Papers
1
Total Citations
5
H-Index
1
About
Montasir Shams is a rising researcher at the forefront of trustworthy AI and multi-modal systems, with a primary focus on the security and robustness of vision-language navigation (VLN). His most-cited work, "Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems" (2024, 5 citations), pioneers a critical line of inquiry into how adversarial inputs can exploit representation vulnerabilities in large language models and multi-modal transformers, causing VLN agents to deviate from intended paths. This research highlights a fundamental tension between the unprecedented capabilities of these models—such as zero-shot recognition and natural language command understanding—and their susceptibility to malicious manipulation. By systematically exposing these attack surfaces, Shams provides essential blueprints for building more resilient autonomous navigation systems. Though early in his career, his work has already garnered attention for its timely relevance as VLN systems move toward real-world deployment. His contributions are vital for students and researchers working at the intersection of computer vision, natural language processing, and AI safety, offering both a cautionary tale and a roadmap for securing the next generation of intelligent agents.
Research Focus
Key Achievements
Top Papers
- 1