2 citations · 3 across the 5 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.CV2025★ 1 cited
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…
eess.AS2025
Efficient Evaluation of Quantization-Effects in Neural Codecs
Wolfgang Mack, Ahmed Mustafa, Rafał Łaganowski +1
Neural codecs, comprising an encoder, quantizer, and decoder, enable signal transmission at exceptionally low bitrates. Training these systems requires techniques like the straight…