5 papers
Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that a…
Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known a…
Efficient Evaluation of Quantization-Effects in Neural Codecs
Wolfgang Mack, Ahmed Mustafa, RafaÅ Åaganowski +1
Neural codecs, comprising an encoder, quantizer, and decoder, enable signal transmission at exceptionally low bitrates. Training these systems requires techniques like the straight…
Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion
Muhammad Tahir Rafique, Ahmed Mustafa, Hasan Sajid
The growing demand for road use in urban areas has led to significant traffic congestion, posing challenges that are costly to mitigate through infrastructure expansion alone. As a…
A Permuted Autoregressive Approach to Word-Level Recognition for Urdu Digital Text
Ahmed Mustafa, Muhammad Tahir Rafique, Muhammad Ijlal Baig +3
This research paper introduces a novel word-level Optical Character Recognition (OCR) model specifically designed for digital Urdu text, leveraging transformer-based architectures…