Accurate lora-finetuning quantization of llms via information retention

H Qin, X Ma, X Zheng, X Li, Y Zhang, S Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate
yet compact LLMs for deployment on resource-constrained hardware. However, existing …

Physical Adversarial Patch Attack for Optical Fine-Grained Aircraft Recognition

K Li, D Wang, W Zhu, S Li, Q Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Deep neural networks (DNNs) have been widely used in remote sensing but demonstrated
to be sensitive with adversarial examples. By introducing carefully designed perturbations to …

Behavior Backdoor for Deep Learning Models

J Wang, P Zhang, R Tao, J Yang, H Liu, X Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
The various post-processing methods for deep-learning-based models, such as
quantification, pruning, and fine-tuning, play an increasingly important role in artificial …

DynamicPAE: Generating Scene-Aware Physical Adversarial Examples in Real-Time

J Hu, X Liu, J Wang, J Zhang, X Yang, H Qin… - arxiv preprint arxiv …, 2024 - arxiv.org
Physical adversarial examples (PAEs) are regarded as" whistle-blowers" of real-world risks
in deep-learning applications. However, current PAE generation studies show limited …

Image Forensics Strikes Back: Defense Against Adversarial Patch

CC Kao, CS Lu, CM Yu - 2024 IEEE International Conference …, 2024 - ieeexplore.ieee.org
Traffic sign recognition plays a crucial role in self-driving cars, but unfortunately, it is
vulnerable to adversarial patches (AP). Although AP can efficiently fool DNN-based models …