|
|
Min Yang 杨 珉
Professor, Executive Dean, AICS, Fudan University Office: A6011, Interdisciplinary Building No.2, Jiangwan Campus, Fudan University Email: m_yang at fudan.edu.cn |
|
I am a Professor and the Executive Dean of the Computation and Artificial Intelligence Innovative College (AICS) at Fudan University. I lead the System Software and Security Lab at Fudan University, which is ranked the 12th worldwide according to the CSRankings based on our research outcomes in the past decade. I received my Bachelor and PhD degree from Fudan University.
|
Awards and Honors
Distinguished Paper Award, NDSS (top-tier cybersecurity conference), 2025
Distinguished Paper Award, ACM SIGSOFT (top-tier software-engineering conference), 2024
USENIX Security Symposium Distinguished Paper Award (top-tier cybersecurity conference), 2023
Distinguished Paper Nomination, ACM CCS (top-tier cybersecurity conference), 2020
Professional Service
Associate Editor: ACM TOPS
Publications
|
OpenDeception: Benchmarking and Investigating AI Deceptive Behaviors via Open-ended Interaction Simulation |
||
|
Large language model-powered AI systems achieve self-replication with no human intervention |
||
|
Exposing the Hidden Layer: Software Repositories in the Service of SEO Manipulation |
||
|
Revealing the Black Box of Device Search Engine: Scanning Assets, Strategies, and Ethical Consideration |
||
|
Frontier AI systems have surpassed the self-replicating red line |
||
|
Are We Getting Well-informed? An In-depth Study of Runtime Privacy Notice Practice in Mobile Apps |
||
|
Rag-thief: Scalable extraction of private data from retrieval-augmented generation applications with agent-based attacks |
||
|
Matryoshka: Exploiting the Over-Parametrization of Deep Learning Models for Covert Data Transmission |
||
|
A proactive trust evaluation system for secure data collection based on sequence extraction |
||
|
Efficient detection of java deserialization gadget chains via bottom-up gadget search and dataflow-aided payload construction |
||
|
BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting |
||
|
Withdrawing is believing? Detecting inconsistencies between withdrawal choices and third-party data collections in mobile apps |
||
|
Rrl: Recommendation reverse learning |
||
|
Sctrans: Constructing a large public scenario dataset for simulation testing of autonomous driving systems |
||
|
Identifying Cross-User Privacy Leakage in Mobile Mini-Apps at a Large Scale |
||
|
Leaking the Privacy of Groups and More: Understanding Privacy Risks of Cross-App Content Sharing in Mobile Ecosystem |
||
|
No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models |
||
|
Trusteddomain compromise attack in app-in-app ecosystems |
||
|
Under the dark: a systematical study of stealthy mining pools (ab)use in the wild |
||
|
Syzdirect: Directed greybox fuzzing for linux kernel |
||
|
Nestfuzz: Enhancing fuzzing with comprehensive understanding of input processing logic |
||
|
Jade: A linguistics-based safety evaluation platform for large language models |
||
|
Cracking white-box dnn watermarks via invariant neuron transforms |
||
|
DARPA: Combating asymmetric dark ui patterns on android with run-time view decorator |
||
|
Black-box adversarial attack on time series classification |
||
|
Understanding privacy over-collection in wechat sub-app ecosystem |
||
|
AEM: Facilitating cross-version exploitability assessment of linux kernel vulnerabilities |
||
|
Recovering call graphs for binaries with transfer and contrastive learning |
||
|
Understanding the (in) security of cross-side face verification systems in mobile apps: A system perspective |
||
|
MASS: Model-agnostic, semantic and stealthy data poisoning attack on knowledge graph embedding |
||
|
Anti-FakeU: Defending shilling attacks on graph neural network based recommender model |
||
|
VenomAttack: Automated and adaptive activity hijacking in Android |
||
|
Exorcising 'Wraith': Protecting LiDAR-based object detector in automated driving system from appearing attacks |
||
|
JADE: A linguistics-based safety evaluation platform for LLM |
||
|
Notice the imposter! A study on user tag spoofing attack in mobile apps |
||
|
Rethinking white-box watermarks on deep learning models under neural structural obfuscation |
||
|
Collect Responsibly But Deliver Arbitrarily? A Study on Cross-User Privacy Leakage in Mobile Apps |
||
|
Precise (un)affected version analysis for web vulnerabilities |
||
|
MetaV: A meta-verifier approach to task-agnostic model fingerprinting |
||
|
Identity Confusion in WebView-based Mobile App-in-app Ecosystems |
||
|
Backporting Security Patches of Web Applications: A Prototype Design and Implementation on Injection Vulnerability Patches |
||
|
Exploring the Security Boundary of Data Reconstruction via Neuron Exclusivity Analysis |
||
|
Ferry: State-Aware Symbolic Execution for Exploring State-Dependent Program Paths |
||
|
Rendering Contention Channel Made Practical in Web Browsers |
||
|
Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model |
||
|
Exploit the Last Straw that Breaks Android Systems |
||
|
Analyzing Ground-Truth Data of Mobile Gambling Scams |
||
|
Towards Backdoor Attack on Deep Learning based Time Series Classification |
||
|
Understanding the Practice of Security Patch Management Across Multiple Branches in OSS Projects |
||
|
Dancing with Wolves: An Intra-Process Isolation Technique with Privileged Hardware |
||
|
Slowing Down the Aging of Learning-Based Malware Detectors with API Knowledge |
||
|
Rendering contention channel made practical in web browsers |
||
|
Hidden trigger backdoor attack on {NLP} models via linguistic style manipulation |
||
|
Understanding the Threats of Trojaned Quantized Neural Network in Model Supply Chains |
||
|
Locating the security patches for disclosed oss vulnerabilities with vulnerability-commit correlation ranking |
||
|
Facilitating vulnerability assessment through poc migration |
||
|
A Deep Learning Framework for Self-evolving Hierarchical Community Detection |
||
|
TAFA: A Task-Agnostic Fingerprinting Algorithm for Neural Networks |
||
|
Enhancing time series predictors with generalized extreme value loss |
||
|
Weak Links in Authentication Chains: A Large-scale Analysis of Email Sender Spoofing Attacks |
||
|
Detecting Kernel Refcount Bugs with Two-Dimensional Consistency Checking |
||
|
From WHOIS to WHOWAS: A Large-Scale Measurement Study of Domain Registration Privacy under the GDPR |
||
|
icallee: Recovering call graphs for binaries |
||
|
Understanding promotion-as-a-service on GitHub |
||
|
Modeling personalized out-of-town distances in location recommendation |
||
|
Enhancing State-of-the-art Classifiers with API Semantics to Detect Evolved Android Malware |
||
|
PDiff: Semantic-based Patch Presence Testing for Downstream Kernels |
||
|
Talking with Familiar Strangers: An Empirical Study on HTTPS Context Confusion Attacks |
||
|
An Ever-evolving Game: Evaluation of Real-world Attacks and Defenses in Ethereum Ecosystem |
||
|
Justinian's GAAvernor: Robust Distributed Learning with Gradient Aggregation Agent |
||
|
BScout: Direct Whole Patch Presence Test for Java Executables |
||
|
TEXTSHIELD: Robust Text Classification Based on Multimodal Embedding and Neural Machine Translation |
||
|
A Geometrical Perspective on Image Style Transfer with Adversarial Learning |
||
|
Privacy Risks of General-Purpose Language Models |
||
|
Efficient and Secure SMAP-Enabled Intra-process Memory Isolation |
||
|
TextExerciser: Feedback-driven Text Input Exercising for Android Applications |
||
|
How Android Developers Handle Evolution-induced API Compatibility Issues: A Large-scale Study |
||
|
Improving the Robustness of Wasserstein Embedding by Adversarial PAC-Bayesian Learning |
||
|
Theory-oriented Deep Leakage from Gradients via Linear Equation Solver |
||
|
Tainting-assisted and Context-migrated Symbolic Execution of Android Framework for Vulnerability Discovery and Exploit Generation |
||
|
Modeling Extreme Events in Time Series Prediction |
||
|
App in the Middle: Demystify Application Virtualization in Android and its Security Threats |
||
|
How You Get Shot in the Back: A Systematical Study about Cryptojacking in the Real World |
||
|
Invetter: Locating Insecure Input Validations in Android Services |
||
|
Detecting third-party libraries in Android applications with high precision and recall |
||
|
Who is answering my queries: Understanding and characterizing interception of the DNS resolution path |
||
|
We Still Don’t Have Secure Cross-Domain Requests: an Empirical Study of CORS |
||
|
An empirical study of web resource manipulation in real-world mobile applications |
||
|
Finding Clues for Your Secrets: Semantics-Driven, Learning-Based Privacy Discovery in Mobile Apps |
||
|
System service call-oriented symbolic execution of android framework with applications to vulnerability discovery and exploit generation |
||
|
Identifying user-input privacy in mobile applications at a large scale |
||
|
A survey of privacy protection techniques for mobile devices |
||
|
Rethinking permission enforcement mechanism on mobile systems |
||
|
Finedroid: Enforcing Permissions with System-Wide Application Execution Context |
||
|
Uipicker: User-Input Privacy Identification in Mobile Applications |
||
|
Permission Use Analysis for Vetting Undesirable Behaviors in Android Apps |
||
|
Cost-Based Optimization of Logical Partitions for a Query Workload in a Hadoop Data Warehouse |
||
|
Cost-Based Join Algorithm Selection in Hadoop |
||
|
Vetting Undesirable Behaviors in Android Apps with Permission Use Analysis |
||
|
Appintent: Analyzing Sensitive Data Transmission in Android for Privacy Leakage Detection |
||
|
Leakminer: Detect Information Leakage on Android with Static Taint Analysis |
||
|
Swift: A Register-Based JIT Compiler for Embedded JVMs |
||
|
ORDER: Object CentRic DEterministic Replay for Java |