An Overview of Trustworthy AI: Advances in IP Protection, Privacy-preserving Federated Learning, Security Verification, and GAI Safety Alignment
AI has undergone a remarkable evolution journey marked by groundbreaking milestones.
Like any powerful tool, it can be turned into a weapon for devastation in the wrong hands …
Like any powerful tool, it can be turned into a weapon for devastation in the wrong hands …
Revisiting Black-box Ownership Verification for Graph Neural Networks
R Zhou, K Yang, X Wang, WH Wang… - 2024 IEEE Symposium on …, 2024 - computer.org
Abstract Graph Neural Networks (GNNs) have emerged as powerful tools for processing
graph-structured data, enabling applications in various domains. Yet, GNNs are vulnerable …
graph-structured data, enabling applications in various domains. Yet, GNNs are vulnerable …
HoneypotNet: Backdoor Attacks Against Model Extraction
Model extraction attacks are one type of inference-time attacks that approximate the
functionality and performance of a black-box victim model by launching a certain number of …
functionality and performance of a black-box victim model by launching a certain number of …
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 …
[PDF][PDF] Protecting object detection models from model extraction attack via feature space coverage
The model extraction attack is an attack pattern aimed at stealing well-trained machine
learning models' functionality or privacy information. With the gradual popularization of AI …
learning models' functionality or privacy information. With the gradual popularization of AI …
AI Risk Management Should Incorporate Both Safety and Security
The exposure of security vulnerabilities in safety-aligned language models, eg, susceptibility
to adversarial attacks, has shed light on the intricate interplay between AI safety and AI …
to adversarial attacks, has shed light on the intricate interplay between AI safety and AI …
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces
In the domain of black-box model extraction, conventional methods reliant on soft labels or
surrogate datasets struggle with scaling to high-dimensional input spaces and managing the …
surrogate datasets struggle with scaling to high-dimensional input spaces and managing the …
DualCOS: Query-Efficient Data-Free Model Stealing with Dual Clone Networks and Optimal Samples
Although data-free model stealing attacks are free from reliance on real data, they suffer
from limitations, including low accuracy and high query budgets, which restrict their practical …
from limitations, including low accuracy and high query budgets, which restrict their practical …
IPES: Improved Pre-trained Encoder Stealing Attack in Contrastive Learning
Recent studies have shed light on security vulnerabilities in Encoder-as-a-Service (EaaS)
systems that enable the theft of valuable encoder attributes such as functionality. However …
systems that enable the theft of valuable encoder attributes such as functionality. However …
PtbStolen: Pre-trained Encoder Stealing Through Perturbed Samples
PtbStolen: Pre-trained Encoder Stealing Through Perturbed Samples | SpringerLink Skip to
main content Advertisement SpringerLink Account Menu Find a journal Publish with us Track …
main content Advertisement SpringerLink Account Menu Find a journal Publish with us Track …