133 citations · 216 across the 26 of their papers we have counts for
27 papers
From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
Qirui Huang, Na Li, Hongsheng Hu +3
To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age es…
Kill Two Birds with One Stone! Trajectory enabled Unified Online Detection of Adversarial Examples and Backdoor Attacks
Anmin Fu, Fanyu Meng, Huaibing Peng +5
The proposed UniGuard is the first unified online detection framework capable of simultaneously addressing adversarial examples and backdoor attacks. UniGuard builds upon two key i…
THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models
Yujin Huang, Zhi Zhang, Qingchuan Zhao +2
On-device deep learning (DL) has rapidly gained adoption in mobile apps, offering the benefits of offline model inference and user privacy preservation over cloud-based approaches.…
Physical and Software Based Fault Injection Attacks Against TEEs in Mobile Devices: A Systemisation of Knowledge
Aaron Joy, Ben Soh, Zhi Zhang +2
Trusted Execution Environments (TEEs) are critical components of modern secure computing, providing isolated zones in processors to safeguard sensitive data and execute secure oper…
Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
Na Li, Chunyi Zhou, Yansong Gao +4
Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the right to be f…
QuanShield: Protecting against Side-Channels Attacks using Self-Destructing Enclaves
Shujie Cui, Haohua Li, Yuanhong Li +3
Trusted Execution Environments (TEEs) allow user processes to create enclaves that protect security-sensitive computation against access from the OS kernel and the hypervisor. Rece…
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
Hua Ma, Shang Wang, Yansong Gao +7
All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class act…
DeepTheft: Stealing DNN Model Architectures through Power Side Channel
Yansong Gao, Huming Qiu, Zhi Zhang +6
Deep Neural Network (DNN) models are often deployed in resource-sharing clouds as Machine Learning as a Service (MLaaS) to provide inference services.To steal model architectures t…
One-to-Multiple Clean-Label Image Camouflage (OmClic) based Backdoor Attack on Deep Learning
Guohong Wang, Hua Ma, Yansong Gao +6
Image camouflage has been utilized to create clean-label poisoned images for implanting backdoor into a DL model. But there exists a crucial limitation that one attack/poisoned ima…
SemDiff: Binary Similarity Detection by Diffing Key-Semantics Graphs
Zian Liu, Zhi Zhang, Xiaoxi Meng +8
Binary similarity detection is a critical technique that has been applied in many real-world scenarios where source code is not available, e.g., bug search, malware analysis, and c…
Imperceptible Sample-Specific Backdoor to DNN with Denoising Autoencoder
Xiangqi Wang, Mingfu Xue, Kewei Chen +4
The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which…
TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World
Hua Ma, Yinshan Li, Yansong Gao +6
Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfacto…
CASSOCK: Viable Backdoor Attacks against DNN in The Wall of Source-Specific Backdoor Defences
Shang Wang, Yansong Gao, Anmin Fu +4
As a critical threat to deep neural networks (DNNs), backdoor attacks can be categorized into two types, i.e., source-agnostic backdoor attacks (SABAs) and source-specific backdoor…
Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures
Huming Qiu, Hua Ma, Zhi Zhang +4
Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumpti…
Systematically Evaluation of Challenge Obfuscated APUFs
Yansong Gao, Jianrong Yao, Lihui Pang +4
As a well-known physical unclonable function that can provide huge number of challenge response pairs (CRP) with a compact design and fully compatibility with current electronic fa…
PPA: Preference Profiling Attack Against Federated Learning
Chunyi Zhou, Yansong Gao, Anmin Fu +5
Federated learning (FL) trains a global model across a number of decentralized users, each with a local dataset. Compared to traditional centralized learning, FL does not require d…
NTD: Non-Transferability Enabled Backdoor Detection
Yinshan Li, Hua Ma, Zhi Zhang +6
A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model d…
Design and Evaluate Recomposited OR-AND-XOR-PUF
Jianrong Yao, Lihui Pang, Zhi Zhang +3
Physical Unclonable Function (PUF) is a hardware security primitive with a desirable feature of low-cost. Based on the space of challenge-response pairs (CRPs), it has two categori…
Quantization Backdoors to Deep Learning Commercial Frameworks
Hua Ma, Huming Qiu, Yansong Gao +7
Currently, there is a burgeoning demand for deploying deep learning (DL) models on ubiquitous edge Internet of Things (IoT) devices attributed to their low latency and high privacy…
RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things
Huming Qiu, Hua Ma, Zhi Zhang +6
Though deep neural network models exhibit outstanding performance for various applications, their large model size and extensive floating-point operations render deployment on mobi…
Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things
Yansong Gao, Minki Kim, Chandra Thapa +5
Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning training without accessing raw data on clien…
SoftTRR: Protect Page Tables Against RowHammer Attacks using Software-only Target Row Refresh
Zhi Zhang, Yueqiang Cheng, Minghua Wang +7
Rowhammer attacks that corrupt level-1 page tables to gain kernel privilege are the most detrimental to system security and hard to mitigate. However, recently proposed software-on…
Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
Yansong Gao, Bao Gia Doan, Zhi Zhang +5
This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attacker's capability and affected st…
PThammer: Cross-User-Kernel-Boundary Rowhammer through Implicit Accesses
Zhi Zhang, Yueqiang Cheng, Dongxi Liu +3
Rowhammer is a hardware vulnerability in DRAM memory, where repeated access to memory can induce bit flips in neighboring memory locations. Being a hardware vulnerability, rowhamme…