René's URL Explorer Experiment


Title: Tianyu Du - Homepage

Open Graph Title: Tianyu Du

Open Graph Description: Assistant Professor at Zhejiang University. Research interests include adversarial machine learning and security of LLMs.

Mail addresses
tydusky@gmail.com
tydusky@gmail.com

Opengraph URL: https://tydusky.github.io/

direct link

Domain: tydusky.github.io

og:localeen
og:site_nameTianyu Du
HandheldFriendlyTrue
MobileOptimized320
Noneon
msapplication-TileColor#000000
msapplication-TileImageimages/mstile-144x144.png?v=M44lzPylqQ
msapplication-configimages/browserconfig.xml?v=M44lzPylqQ
theme-color#ffffff

Links:

Homepagehttps://tydusky.github.io/#about-me
About Mehttps://tydusky.github.io/#about-me
Publicationshttps://tydusky.github.io/#-publications
Google Scholarhttps://scholar.google.com/citations?user=kBqTzrwAAAAJ
https://scholar.google.com/citations?user=kBqTzrwAAAAJ
Ting Wanghttps://alps-lab.github.io/
Shouling Jihttps://nesa.zju.edu.cn/webpage/crew/jsl.html
Bo Lihttps://aisecure.github.io/
Ting Wanghttps://alps-lab.github.io/
Tao Weihttps://scholar.google.com/citations?user=Ao3wEckAAAAJ&hl=zh-CN
Jie Shihttps://scholar.google.com/citations?user=GQJDlW8AAAAJ&hl=zh-CN
VIS 2026https://ieeevis.org
CCS 2026https://www.sigsac.org/ccs/CCS2026/
CCS 2026https://www.sigsac.org/ccs/CCS2026/
KDD 2026https://kdd2026.kdd.org/
TIFS 2026https://signalprocessingsociety.org/publications-resources/ieee-transactions-information-forensics-and-security
ICML 2026https://icml.cc/
ICDM 2026http://icdm2026.neu.edu.cn/main.htm
ICMR 2026https://www.icmr2026.org/
ACL 2026https://2026.aclweb.org/
ICLR 2026https://iclr.cc/
WWW 2026https://www2026.thewebconf.org/
KDD 2026https://kdd2026.kdd.org/
TIFS 2025https://signalprocessingsociety.org/publications-resources/ieee-transactions-information-forensics-and-security
AAAI 2026https://aaai.org/conference/aaai/aaai-26/
EMNLP 2025https://2025.emnlp.org/
MM 2025https://acmmm2025.org/
ICCV 2025https://iccv.thecvf.com/
ACL 2025https://2025.aclweb.org/
IJCAI 2025https://2025.ijcai.org/
ICLR 2025https://iclr.cc/
AAAI 2025https://aaai.org/conference/aaai/aaai-25/
COLING 2025https://coling2025.org/
EMNLP 2024https://2024.emnlp.org/
NDSS 2025https://www.ndss-symposium.org/ndss2025/
MM 2024https://2024.acmmm.org/
CCS 2024https://www.sigsac.org/ccs/CCS2024/
ACL 2024https://2024.aclweb.org/
ICLR 2024https://iclr.cc/Conferences/2024
NeurIPS 2023https://nips.cc/
ICCV 2023https://iccv2023.thecvf.com/
USENIX Security 2023https://www.usenix.org/conference/usenixsecurity23
Cybersecurityhttps://cybersecurity.springeropen.com/about
Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networkshttps://dl.acm.org/doi/10.1145/3460120.3484538
TextShield: Robust Text Classification Based on Multimodal Embedding and Neural Machine Translationhttps://www.usenix.org/system/files/sec20-li-jinfeng.pdf
TextBugger: Generating Adversarial Text Against Real-world Applicationshttps://www.ndss-symposium.org/wp-content/uploads/2019/02/ndss2019_03A-5_Li_paper.pdf
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Modelshttps://tydusky.github.io/
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applicationshttps://tydusky.github.io/
Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystemhttps://tydusky.github.io/
The Boy Who Cried Wolf: Adversarial Misclassification of Safe Inputs as Unsafe in Multimodal Guardrailshttps://tydusky.github.io/
LoRAShield: Data-Free Editing Alignment for Secure Personalized LoRA Sharinghttps://tydusky.github.io/
Leveraging Machine Unlearning for Cost-Efficient Preference Alignmenthttps://tydusky.github.io/
Content-Adaptive Implicit Neural Representations for Resolution-Agnostic Remote Sensing Watermarkinghttps://tydusky.github.io/
ACIArena: Toward Unified Evaluation for Agent Cascading Injectionhttps://arxiv.org/abs/2604.07775
“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns?https://arxiv.org/pdf/2604.05930
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoorshttps://tydusky.github.io/
PerMemSafe: Benchmarking Implicit Personalized Safety of Long Horizon Self-Evolving Agentshttps://tydusky.github.io/
When Agents “Misremember” Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systemshttps://openreview.net/forum?id=yIoMqDes7O
FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attackshttps://arxiv.org/abs/2601.22485
The Eminence in Shadow: Exploiting Feature Boundary Ambiguity for Robust Backdoor Attackshttps://arxiv.org/abs/2512.10402
Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?https://arxiv.org/abs/2512.21871
HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectorshttps://arxiv.org/abs/2601.05587
DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Datahttps://arxiv.org/pdf/2511.09876
FedAU^2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Traininghttps://arxiv.org/abs/2511.22872
LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mappinghttps://arxiv.org/pdf/2511.01296
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agentshttps://arxiv.org/abs/2508.15310
VideoEraser: Concept Erasure in Text-to-Video Diffusion Modelshttps://arxiv.org/abs/2508.15314
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracinghttps://arxiv.org/abs/2509.13982
Enkidu: Universal Frequential Perturbation for Real-Time Audio Privacy Protection against Voice Deepfakeshttps://arxiv.org/abs/2507.12932
An Inversion-based Measure of Memorization for Diffusion Modelshttps://arxiv.org/abs/2405.05846
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Questionhttps://arxiv.org/abs/2506.00823v1
Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterizationhttps://arxiv.org/abs/2505.05017
CollabEdit: Towards Non-destructive Collaborative Knowledge Editinghttps://arxiv.org/abs/2410.09508
Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understandinghttps://arxiv.org/abs/2410.01671
Tool-Planner: Task Planning with Clusters across Multiple Toolshttps://arxiv.org/abs/2406.03807
DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Modelshttps://arxiv.org/abs/2406.11087
DROWN: Towards Tighter LiRPA-based Robustness Certificationhttps://arxiv.org/abs/2304.07980
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Modelshttps://arxiv.org/abs/2409.01193
SecCoder: Towards Generalizable and Robust Secure Code Generationhttps://arxiv.org/abs/2410.01488
TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deploymenthttps://arxiv.org/pdf/2404.11121
Cons2Plan: Vector Floorplan Generation from Various Conditions via a Learning Framework based on Conditional Diffusion Modelshttps://dl.acm.org/doi/10.1145/3664647.3680681
Unveiling the Vulnerability of Private Fine-Tuning in Split-Based Frameworks for Large Language Models: A Bidirectionally Enhanced Attackhttps://arxiv.org/abs/2409.00960
ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysishttps://arxiv.org/pdf/2403.06932
RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedbackhttps://arxiv.org/pdf/2403.06840
ReMasker: Imputing Tabular Data with Masked Autoencodinghttps://openreview.net/forum?id=KI9NqjLVDT
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attackshttps://openreview.net/pdf?id=GqXbfVmEPW
UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbationhttps://openreview.net/pdf?id=oGxE2Nvlda
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Modelshttps://openreview.net/pdf?id=qBAED3u1XZ
An Embarrassingly Simple Self-supervised Trojan Attackhttps://arxiv.org/abs/2210.07346
On the Security Risks of Knowledge Graph Reasoninghttps://arxiv.org/pdf/2305.02383.pdf
NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identificationhttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9793943
Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networkshttps://dl.acm.org/doi/10.1145/3460120.3484538
Enhancing Model Robustness by Incorporating Adversarial Knowledge into Semantic Representationhttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9414793
SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systemshttps://par.nsf.gov/servlets/purl/10174631
TextShield: Robust Text Classification Based on Multimodal Embedding and Neural Machine Translationhttps://www.usenix.org/system/files/sec20-li-jinfeng.pdf
TextBugger: Generating Adversarial Text Against Real-world Applicationshttps://www.ndss-symposium.org/wp-content/uploads/2019/02/ndss2019_03A-5_Li_paper.pdf
Invisible Poisoning: Highly Stealthy Targeted Poisoning Attackhttps://www.researchgate.net/profile/Chen-Jinyin/publication/340423472_Invisible_Poisoning_Highly_Stealthy_Targeted_Poisoning_Attack/links/5f841dc9a6fdccfd7b5aa812/Invisible-Poisoning-Highly-Stealthy-Targeted-Poisoning-Attack.pdf
Symmetric Frame Cracking: a Powerful Dynamic Textual CAPTCHA Cracking Policyhttps://link.springer.com/chapter/10.1007/978-3-030-42921-8_9
Neural Network Model for Classifying the Economic Recession and Construction of Financial Stress Indexhttps://link.springer.com/chapter/10.1007/978-981-15-0121-0_44
Quantifying Graph Anonymity, Utility, and De-anonymityhttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8486356
Online E-Commerce Fraud: A Large-scale Detection and Analysishttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8509383
You Are What You Search: Attribute Inference Attacks Through Web Search Querieshttps://link.springer.com/chapter/10.1007/978-3-030-16946-6_27
Static taint analysis method for intent injection vulnerability in android applicationshttps://nesa.zju.edu.cn/download/Static%20Taint%20Analysis%20Method%20for%20Intent%20Injection%20Vulnerability%20in%20Android%20Applications.pdf
Influence Spread in Social Networks with both Positive and Negative Influenceshttps://nesa.zju.edu.cn/download/Influence%20Spread%20in%20Social%20Networks%20with%20Both%20Positive%20and%20Negative%20Influences.pdf
Automatic Red Teaming LLM-based Agents with Model Context Protocol Toolshttps://arxiv.org/abs/2509.21011
G^2uardFL: Safeguarding Federated Learning against Backdoor Attacks via Attributed Client Graph Clusteringhttps://arxiv.org/abs/2306.04984
DetectSec: Evaluating the Robustness of Object Detection Models to Adversarial Attackshttps://onlinelibrary.wiley.com/doi/pdf/10.1002/int.22851
Your labels are selling you out: Relation leaks in vertical federated learninghttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=9899694
FineFool: A Novel DNN Object Contour Attack on Image Recognition Based on the Attention Perturbation Adversarial Techniquehttps://www.sciencedirect.com/science/article/pii/S0167404821000444
Robustness Certification Research on Deep Learning Models: A Surveyhttp://159.226.43.17/online/bfpub/jsl-2021128163639.pdf
Security and Privacy of Machine Learning Models: A Surveyhttps://www.jos.org.cn/jos/article/pdf/6131
Survey on Techniques, Applications and Security of Machine Learning Interpretabilityhttps://crad.ict.ac.cn/cn/article/doi/10.7544/issn1000-1239.2019.20190540
Spreading Social Influence with Both Positive and Negative Opinions in Online Networkshttps://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8665728
SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systemshttps://nesa.zju.edu.cn/download/SirenAttack%20Generating%20Adversarial%20Audio%20for%20End-to-End%20Acoustic%20Systems.pdf
EMNLP 2023https://2023.emnlp.org/
ACL 2023https://2023.aclweb.org/
Cybersecurityhttps://cybersecurity.springeropen.com/about

Viewport: width=device-width, initial-scale=1.0

URLs of crawlers that visited me.