What Makes a Good Dataset for Knowledge Distillation?
Knowledge distillation (KD) has been a popular and effective method for model
compression. One important assumption of KD is that the teacher's original dataset will also …
compression. One important assumption of KD is that the teacher's original dataset will also …
Attention-SA: Exploiting Model-approximated Data Semantics for Adversarial Attack
Adversarial Defense of deep neural networks have gained significant attention and there
have been active research efforts on model blind-points for attacking such as gradient …
have been active research efforts on model blind-points for attacking such as gradient …
SoK: Dataset Copyright Auditing in Machine Learning Systems
As the implementation of machine learning (ML) systems becomes more widespread,
especially with the introduction of larger ML models, we perceive a spring demand for …
especially with the introduction of larger ML models, we perceive a spring demand for …
Intellectual Property Protection for Deep Learning Model and Dataset Intelligence
With the growing applications of Deep Learning (DL), especially recent spectacular
achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the …
achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the …
Know2Vec: A Black-Box Proxy for Neural Network Retrieval
Z Shang, Y Liu, J Liu, X Gu, Y Ding, X Ji - arXiv preprint arXiv:2412.16251, 2024 - arxiv.org
For general users, training a neural network from scratch is usually challenging and labor-
intensive. Fortunately, neural network zoos enable them to find a well-performing model for …
intensive. Fortunately, neural network zoos enable them to find a well-performing model for …
Robust Hashing for Neural Network Models via Heterogeneous Graph Representation
L Huang, Y Tao, C Qin, X Zhang - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
How to protect the intellectual property (IP) of neural network models has become a hot topic
in current research. Model hashing as an important model protection scheme, which …
in current research. Model hashing as an important model protection scheme, which …
Take Fake as Real: Realistic-like Robust Black-box Adversarial Attack to Evade AIGC Detection
The security of AI-generated content (AIGC) detection based on GANs and diffusion models
is closely related to the credibility of multimedia content. Malicious adversarial attacks can …
is closely related to the credibility of multimedia content. Malicious adversarial attacks can …
Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Images
Knowledge distillation (KD) has been a popular and effective method for model
compression. One important assumption of KD is that the original training dataset is always …
compression. One important assumption of KD is that the original training dataset is always …