7 citations · 8 across the 4 of their papers we have counts for
4 papers
An Engorgio Prompt Makes Large Language Model Babble on
Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang +7
Auto-regressive large language models (LLMs) have yielded impressive performance in many real-world tasks. However, the new paradigm of these LLMs also exposes novel threats. In th…
COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation
Ziyuan Zhang, Han Qiu, Maosen Zhang +4
With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmiss…
Aegis: Mitigating Targeted Bit-flip Attacks against Deep Neural Networks
Jialai Wang, Ziyuan Zhang, Meiqi Wang +6
Bit-flip attacks (BFAs) have attracted substantial attention recently, in which an adversary could tamper with a small number of model parameter bits to break the integrity of DNNs…
Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing
Tian Dong, Ziyuan Zhang, Han Qiu +3
Transforming off-the-shelf deep neural network (DNN) models into dynamic multi-exit architectures can achieve inference and transmission efficiency by fragmenting and distributing…