333 citations · 1.3k across the 71 of their papers we have counts for
75 papers
G-Fuzz: A Directed Fuzzing Framework for gVisor
Yuwei Li, Yuan Chen, Shouling Ji +6
gVisor is a Google-published application-level kernel for containers. As gVisor is lightweight and has sound isolation, it has been widely used in many IT enterprises \cite{Stripe,…
SyzTrust: State-aware Fuzzing on Trusted OS Designed for IoT Devices
Qinying Wang, Boyu Chang, Shouling Ji +8
Trusted Execution Environments (TEEs) embedded in IoT devices provide a deployable solution to secure IoT applications at the hardware level. By design, in TEEs, the Trusted Operat…
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
Zhaohan Xi, Tianyu Du, Changjiang Li +5
Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this…
On the Security Risks of Knowledge Graph Reasoning
Zhaohan Xi, Tianyu Du, Changjiang Li +6
Knowledge graph reasoning (KGR) -- answering complex logical queries over large knowledge graphs -- represents an important artificial intelligence task, entailing a range of appli…
UVSCAN: Detecting Third-Party Component Usage Violations in IoT Firmware
Binbin Zhao, Shouling Ji, Xuhong Zhang +5
Nowadays, IoT devices integrate a wealth of third-party components (TPCs) in firmware to shorten the development cycle. TPCs usually have strict usage specifications, e.g., checkin…
Tram: A Token-level Retrieval-augmented Mechanism for Source Code Summarization
Tong Ye, Lingfei Wu, Tengfei Ma +5
Automatically generating human-readable text describing the functionality of a program is the intent of source code summarization. Although neural language models achieve significa…
RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networks
Yunruo Zhang, Tianyu Du, Shouling Ji +2
It is well-known that recurrent neural networks (RNNs), although widely used, are vulnerable to adversarial attacks including one-frame attacks and multi-frame attacks. Though a fe…
Diff-ID: An Explainable Identity Difference Quantification Framework for DeepFake Detection
Chuer Yu, Xuhong Zhang, Yuxuan Duan +5
Despite the fact that DeepFake forgery detection algorithms have achieved impressive performance on known manipulations, they often face disastrous performance degradation when gen…
Watch Out for the Confusing Faces: Detecting Face Swapping with the Probability Distribution of Face Identification Models
Yuxuan Duan, Xuhong Zhang, Chuer Yu +3
Recently, face swapping has been developing rapidly and achieved a surprising reality, raising concerns about fake content. As a countermeasure, various detection approaches have b…
Edge Deep Learning Model Protection via Neuron Authorization
Jinyin Chen, Haibin Zheng, Tao Liu +4
With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things. Edge device mod…
MINER: A Hybrid Data-Driven Approach for REST API Fuzzing
Chenyang Lyu, Jiacheng Xu, Shouling Ji +6
In recent years, REST API fuzzing has emerged to explore errors on a cloud service. Its performance highly depends on the sequence construction and request generation. However, exi…
FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases
Chong Fu, Xuhong Zhang, Shouling Ji +4
Trojan attack on deep neural networks, also known as backdoor attack, is a typical threat to artificial intelligence. A trojaned neural network behaves normally with clean inputs.…
TextDefense: Adversarial Text Detection based on Word Importance Entropy
Lujia Shen, Xuhong Zhang, Shouling Ji +4
Currently, natural language processing (NLP) models are wildly used in various scenarios. However, NLP models, like all deep models, are vulnerable to adversarially generated text.…
Towards Comprehensively Understanding the Run-time Security of Programmable Logic Controllers: A 3-year Empirical Study
Rongkuan Ma, Qiang Wei, Jingyi Wang +5
Programmable Logic Controllers (PLCs) are the core control devices in Industrial Control Systems (ICSs), which control and monitor the underlying physical plants such as power grid…
One Bad Apple Spoils the Barrel: Understanding the Security Risks Introduced by Third-Party Components in IoT Firmware
Binbin Zhao, Shouling Ji, Jiacheng Xu +8
Currently, the development of IoT firmware heavily depends on third-party components (TPCs) to improve development efficiency. Nevertheless, TPCs are not secure, and the vulnerabil…
HashVFL: Defending Against Data Reconstruction Attacks in Vertical Federated Learning
Pengyu Qiu, Xuhong Zhang, Shouling Ji +3
Vertical Federated Learning (VFL) is a trending collaborative machine learning model training solution. Existing industrial frameworks employ secure multi-party computation techniq…
Neural Architectural Backdoors
Ren Pang, Changjiang Li, Zhaohan Xi +2
This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we…
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
Changjiang Li, Ren Pang, Zhaohan Xi +4
As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to…
Reasoning over Multi-view Knowledge Graphs
Zhaohan Xi, Ren Pang, Changjiang Li +4
Recently, knowledge representation learning (KRL) is emerging as the state-of-the-art approach to process queries over knowledge graphs (KGs), wherein KG entities and the query are…
"Is your explanation stable?": A Robustness Evaluation Framework for Feature Attribution
Yuyou Gan, Yuhao Mao, Xuhong Zhang +5
Understanding the decision process of neural networks is hard. One vital method for explanation is to attribute its decision to pivotal features. Although many algorithms are propo…
MPInspector: A Systematic and Automatic Approach for Evaluating the Security of IoT Messaging Protocols
Qinying Wang, Shouling Ji, Yuan Tian +8
Facilitated by messaging protocols (MP), many home devices are connected to the Internet, bringing convenience and accessibility to customers. However, most deployed MPs on IoT pla…
VeriFi: Towards Verifiable Federated Unlearning
Xiangshan Gao, Xingjun Ma, Jingyi Wang +5
Federated learning (FL) is a collaborative learning paradigm where participants jointly train a powerful model without sharing their private data. One desirable property for FL is…
Improving Long Tailed Document-Level Relation Extraction via Easy Relation Augmentation and Contrastive Learning
Yangkai Du, Tengfei Ma, Lingfei Wu +4
Towards real-world information extraction scenario, research of relation extraction is advancing to document-level relation extraction(DocRE). Existing approaches for DocRE aim to…
Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings
Yuhao Mao, Chong Fu, Saizhuo Wang +7
One intriguing property of adversarial attacks is their "transferability" -- an adversarial example crafted with respect to one deep neural network (DNN) model is often found effec…