Researcher at CCN University of Science and Technology
I'm a first year Computer Science and Engineering undergraduate with the developing research interest in automated detection of online harm, particularly the gap between how easily malicious concent evades current moderation systems and the scale at which it should be caught. This interest grew out of observing concrete failures in existence performs, harassment and abusive language embedded as text within images bypass conventional text-based filters, reporting mechanisms often require disproportionate volume of user reports before content is actioned, and detection for AI-generated deepfakes and child-safety threats lags dangerously behind the pace of the problem. I'm drawn specifically to the multimodal nature of this challenge: combining natural language processing, computer vision and network analysis to detect not just individual pieces of harmful content but co-ordinated harassment patterns and cross-platform abuse that evade single-system detection. My longer-term goal is graduate study in AI/ML with a specialization in trust and safety systems, working toward detection technology that intervenes proactively rather than reactively.