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 …
Gotcha! i know what you are doing on the fpga cloud: Fingerprinting co-located cloud fpga accelerators via measuring communication links
In recent decades, due to the emerging requirements of computation acceleration, cloud
FPGAs have become popular in public clouds. Major cloud service providers, eg AWS and …
FPGAs have become popular in public clouds. Major cloud service providers, eg AWS and …
Disposable identities: Solving web tracking
JB Abdo, S Zeadally - Journal of Information Security and Applications, 2024 - Elsevier
Interrupting the web tracking kill chain is enough to disrupt the tracker's ability to leverage
the collected information; however, this may disrupt the personalized services enjoyed by …
the collected information; however, this may disrupt the personalized services enjoyed by …
Ezclone: Improving dnn model extraction attack via shape distillation from gpu execution profiles
Deep Neural Networks (DNNs) have become ubiquitous due to their performance on
prediction and classification problems. However, they face a variety of threats as their usage …
prediction and classification problems. However, they face a variety of threats as their usage …
[PDF][PDF] SoK: neural network extraction through physical side channels
SoK Neural Network Extraction-USENIX Presentation Page 1 SoK: Neural Network Extraction
Through Physical Side Channels 15.08.2024 Péter Horváth, Dirk Lauret, Zhuoran Liu, and …
Through Physical Side Channels 15.08.2024 Péter Horváth, Dirk Lauret, Zhuoran Liu, and …
Enabling DVFS Side-Channel Attacks for Neural Network Fingerprinting in Edge Inference Services
The Inference-as-a-Service (IaaS) delivery model provides users access to pre-trained deep
neural networks while safeguarding network code and weights. However, IaaS is not …
neural networks while safeguarding network code and weights. However, IaaS is not …
Extracting DNN Architectures via Runtime Profiling on Mobile GPUs
Deep Neural Networks (DNNs) have become invaluable intellectual property for AI providers
due to advancements fueled by a decade of research and development. However, recent …
due to advancements fueled by a decade of research and development. However, recent …
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 …
Stealing the Invisible: Unveiling Pre-Trained CNN Models through Adversarial Examples and Timing Side-Channels
Machine learning, with its myriad applications, has become an integral component of
numerous technological systems. A common practice in this domain is the use of transfer …
numerous technological systems. A common practice in this domain is the use of transfer …
АНАЛІЗ МЕТОДІВ НАВЧАННЯ ТА ІНСТРУМЕНТІВ НЕЙРОМЕРЕЖ ДЛЯ ВИЯВЛЕННЯ ФЕЙКІВ
В Тищенко - Електронне фахове наукове видання « …, 2023 - csecurity.kubg.edu.ua
Анотація У цій статті проводиться аналіз різних методів навчання та інструментів
нейромереж для виявлення фейків. Розглядаються підходи до виявлення фейків на …
нейромереж для виявлення фейків. Розглядаються підходи до виявлення фейків на …