10 citations · 28 across the 14 of their papers we have counts for
17 papers
Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
Zihan Zhang, Shuangjie Yao, Zesen Liu +8
Semantic caches reduce LLM serving costs by reusing previously generated answers for semantically similar queries. However, retrieval is based solely on embedding similarity betwee…
PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks
Yudong Gao, Qingyue Wang, Yuanyuan Yuan +4
Mixture-of-Experts (MoE) large language models represent high-value intellectual property, yet existing watermarking schemes designed for dense models fail on MoE architectures due…
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Yukun Chen, Boheng Li, Yu Yuan +5
Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to li…
How Multi-Modal LLMs Reshape Visual Deep Learning Testing? A Comprehensive Study Through the Lens of Image Mutation
Liwen Wang, Yuanyuan Yuan, Ao Sun +4
Visual deep learning (VDL) systems have shown significant success in real-world applications like image recognition, object detection, and autonomous driving. To evaluate the relia…
Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learning
Ao Sun, Yuanyuan Yuan, Pingchuan Ma +1
Concept Bottleneck Models (CBMs) aim to deliver interpretable and interventionable predictions by bridging features and labels with human-understandable concepts. While recent CBMs…
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML
Ziqi Zhang, Chen Gong, Yifeng Cai +5
On-device ML introduces new security challenges: DNN models become white-box accessible to device users. Based on white-box information, adversaries can conduct effective model ste…
Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
Yanzuo Chen, Zhibo Liu, Yuanyuan Yuan +3
Bit-flip attacks (BFAs) can manipulate deep neural networks (DNNs). For high-level DNN models running on deep learning (DL) frameworks like PyTorch, extensive BFAs have been used t…
Precise and Generalized Robustness Certification for Neural Networks
Yuanyuan Yuan, Shuai Wang, Zhendong Su
The objective of neural network (NN) robustness certification is to determine if a NN changes its predictions when mutations are made to its inputs. While most certification resear…
Explain Any Concept: Segment Anything Meets Concept-Based Explanation
Ao Sun, Pingchuan Ma, Yuanyuan Yuan +1
EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixe…
Unveiling Hidden DNN Defects with Decision-Based Metamorphic Testing
Yuanyuan Yuan, Qi Pang, Shuai Wang
Contemporary DNN testing works are frequently conducted using metamorphic testing (MT). In general, de facto MT frameworks mutate DNN input images using semantics-preserving mutati…
Decompiling x86 Deep Neural Network Executables
Zhibo Liu, Yuanyuan Yuan, Shuai Wang +2
Due to their widespread use on heterogeneous hardware devices, deep learning (DL) models are compiled into executables by DL compilers to fully leverage low-level hardware primitiv…
CacheQL: Quantifying and Localizing Cache Side-Channel Vulnerabilities in Production Software
Yuanyuan Yuan, Zhibo Liu, Shuai Wang
Cache side-channel attacks extract secrets by examining how victim software accesses cache. To date, practical attacks on cryptosystems and media libraries are demonstrated under d…
ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems
Qi Pang, Yuanyuan Yuan, Shuai Wang +1
Vertical federated learning (VFL) system has recently become prominent as a concept to process data distributed across many individual sources without the need to centralize it. Mu…
Automated Side Channel Analysis of Media Software with Manifold Learning
Yuanyuan Yuan, Qi Pang, Shuai Wang
The prosperous development of cloud computing and machine learning as a service has led to the widespread use of media software to process confidential media data. This paper explo…
MDPFuzz: Testing Models Solving Markov Decision Processes
Qi Pang, Yuanyuan Yuan, Shuai Wang
The Markov decision process (MDP) provides a mathematical framework for modeling sequential decision-making problems, many of which are crucial to security and safety, such as auto…
Provably Valid and Diverse Mutations of Real-World Media Data for DNN Testing
Yuanyuan Yuan, Qi Pang, Shuai Wang
Deep neural networks (DNNs) often accept high-dimensional media data (e.g., photos, text, and audio) and understand their perceptual content (e.g., a cat). To test DNNs, diverse in…
Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion
Yuanyuan Yuan, Qi Pang, Shuai Wang
Various deep neural network (DNN) coverage criteria have been proposed to assess DNN test inputs and steer input mutations. The coverage is characterized via neurons having certain…