5 papers
: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models
Wonwoo Choi, Minjae Seo, Minkyoo Song +3
The rapid evolution of text-to-image (T2I) models has enabled high-fidelity visual synthesis on a global scale. However, these advancements have introduced significant security ris…
HarassGuard: Detecting Harassment Behaviors in Social Virtual Reality with Vision-Language Models
Junhee Lee, Minseok Kim, Hwanjo Heo +2
Social Virtual Reality (VR) platforms provide immersive social experiences but also expose users to serious risks of online harassment. Existing safety measures are largely reactiv…
SecTracer: A Framework for Uncovering the Root Causes of Network Intrusions via Security Provenance
Seunghyeon Lee, Hyunmin Seo, Hwanjo Heo +3
Modern enterprise networks comprise diverse and heterogeneous systems that support a wide range of services, making it challenging for administrators to track and analyze sophistic…
Illusion Worlds: Deceptive UI Attacks in Social VR
Junhee Lee, Hwanjo Heo, Seungwon Woo +3
Social Virtual Reality (VR) platforms have surged in popularity, yet their security risks remain underexplored. This paper presents four novel UI attacks that covertly manipulate u…
EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models
Minjae Seo, Myoungsung You, Junhee Lee +4
Vision models are increasingly deployed in critical applications such as autonomous driving and CCTV monitoring, yet they remain susceptible to resource-consuming attacks. In this…