Skip to content
Log in

Author

M. Aktas

h-index 7 View on Semantic Scholar

We have 2 of 33 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jun 2026

Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models

This study systematically examines the vulnerabilities of open and closed-weight LVLMs, including LLaVA, InstructBLIP, Fuyu, Qwen, DeepSeek, Gemini, GPT, and Grok, using adversarial prompting strategies informed by social theories to simulate real-world social manipulation tactics.

Abdulkadir Erol, Trilok Padhi, Agnik Saha et al. · 0 citations