19 citations · 93 across the 19 of their papers we have counts for
19 papers
DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization
Simin Chen, Shiyi Wei, Cong Liu +1
DL compiler's primary function is to translate DNN programs written in high-level DL frameworks such as PyTorch and TensorFlow into portable executables. These executables can then…
MIMONet: Multi-Input Multi-Output On-Device Deep Learning
Zexin Li, Xiaoxi He, Yufei Li +3
Future intelligent robots are expected to process multiple inputs simultaneously (such as image and audio data) and generate multiple outputs accordingly (such as gender and emotio…
SlothSpeech: Denial-of-service Attack Against Speech Recognition Models
Mirazul Haque, Rutvij Shah, Simin Chen +3
Deep Learning (DL) models have been popular nowadays to execute different speech-related tasks, including automatic speech recognition (ASR). As ASR is being used in different real…
Dynamic Transformers Provide a False Sense of Efficiency
Yiming Chen, Simin Chen, Zexin Li +4
Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream appr…
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
Yufei Li, Zexin Li, Yingfan Gao +1
Pre-trained transformers are popular in state-of-the-art dialogue generation (DG) systems. Such language models are, however, vulnerable to various adversarial samples as studied i…
Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
Zexin Li, Bangjie Yin, Taiping Yao +4
A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i.e., inaccessible gradient and parameter information…
X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection
Aishan Liu, Jun Guo, Jiakai Wang +6
Adversarial attacks are valuable for evaluating the robustness of deep learning models. Existing attacks are primarily conducted on the visible light spectrum (e.g., pixel-wise tex…
SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
Junfeng Guo, Yiming Li, Xun Chen +3
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation.…
DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks
Simin Chen, Mirazul Haque, Cong Liu +1
Today, an increasing number of Adaptive Deep Neural Networks (AdNNs) are being used on resource-constrained embedded devices. We observe that, similar to traditional software, redu…
Learning to Reverse DNNs from AI Programs Automatically
Simin Chen, Hamed Khanpour, Cong Liu +1
With the privatization deployment of DNNs on edge devices, the security of on-device DNNs has raised significant concern. To quantify the model leakage risk of on-device DNNs autom…
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
Simin Chen, Zihe Song, Mirazul Haque +2
Neural image caption generation (NICG) models have received massive attention from the research community due to their excellent performance in visual understanding. Existing work…
EREBA: Black-box Energy Testing of Adaptive Neural Networks
Mirazul Haque, Yaswanth Yadlapalli, Wei Yang +1
Recently, various Deep Neural Network (DNN) models have been proposed for environments like embedded systems with stringent energy constraints. The fundamental problem of determini…
PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning
Junfeng Guo, Ang Li, Cong Liu
While real-world applications of reinforcement learning are becoming popular, the security and robustness of RL systems are worthy of more attention and exploration. In particular,…
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
Junfeng Guo, Ang Li, Cong Liu
Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training…
Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
Bangjie Yin, Wenxuan Wang, Taiping Yao +5
Deep neural networks, particularly face recognition models, have been shown to be vulnerable to both digital and physical adversarial examples. However, existing adversarial exampl…
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection
Xin Dong, Junfeng Guo, Ang Li +3
Various approaches have been proposed for out-of-distribution (OOD) detection by augmenting models, input examples, training sets, and optimization objectives. Deviating from exist…
PredCoin: Defense against Query-based Hard-label Attack
Junfeng Guo, Yaswanth Yadlapalli, Thiele Lothar +2
Many adversarial attacks and defenses have recently been proposed for Deep Neural Networks (DNNs). While most of them are in the white-box setting, which is impractical, a new clas…
LINTS^RT: A Learning-driven Testbed for Intelligent Scheduling in Embedded Systems
Zelun Kong, Yaswanth Yadlapalli, Soroush Bateni +2
Due to the increasing complexity seen in both workloads and hardware resources in state-of-the-art embedded systems, developing efficient real-time schedulers and the corresponding…
PoisHygiene: Detecting and Mitigating Poisoning Attacks in Neural Networks
Junfeng Guo, Ting Wang, Cong Liu
The black-box nature of deep neural networks (DNNs) facilitates attackers to manipulate the behavior of DNN through data poisoning. Being able to detect and mitigate poisoning atta…