3 papers
cs.CV2026
QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing
Shubin Lu, Jiaqi Yin, Yihao Huang
Typographic attacks pose a critical threat to vision-language models (VLMs) by injecting misleading text into images and causing models to rely on adversarial textual cues rather t…
cs.CY2025
Unveiling AI's Threats to Child Protection: Regulatory efforts to Criminalize AI-Generated CSAM and Emerging Children's Rights Violations
Emmanouela Kokolaki, Paraskevi Fragopoulou
This paper aims to present new alarming trends in the field of child sexual abuse through imagery, as part of SafeLine's research activities in the field of cybercrime, child sexua…
cs.CY2024
Navigating the Future of Education: Educators' Insights on AI Integration and Challenges in Greece, Hungary, Latvia, Ireland and Armenia
Evangelia Daskalaki, Katerina Psaroudaki, Paraskevi Fragopoulou
Understanding teachers' perspectives on AI in Education (AIEd) is crucial for its effective integration into the educational framework. This paper aims to explore how teachers curr…