My publication list can also be found at DBLP and Google Scholar, however, they may not be up to date.

2025

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

pdf arxiv code

When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs

pdf arxiv code

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

pdf arxiv code

White-box Membership Inference Attacks against Diffusion Models

pdf arxiv

A Comprehensive Study of Privacy Risks in Curriculum Learning

pdf arxiv

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks

pdf arxiv code

GPTracker: A Large-Scale Measurement of Misused GPTs

pdf arxiv code

On the Effectiveness of Prompt Stealing Attacks on In-The-Wild Prompts

pdf arxiv code

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

pdf arxiv

Towards Understanding Unsafe Video Generation

pdf arxiv code dataset

Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?

pdf arxiv code

2024

The Death and Life of Great Prompts: Analyzing the Evolution of LLM Prompts from the Structural Perspective

pdf arxiv code

ModScan: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities

pdf arxiv code

Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

pdf arxiv code

Membership Inference Attacks Against In-Context Learning

pdf arxiv code

Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution

pdf arxiv code

BadMerging: Backdoor Attacks Against Model Merging

pdf arxiv code

ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models

pdf arxiv code

SeqMIA: Sequential-Metric Based Membership Inference Attack

pdf arxiv code

MGTBench: Benchmarking Machine-Generated Text Detection

pdf arxiv code

"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models

pdf arxiv code dataset Media Coverage: New Scientist, Deutschlandfunk Nova

Instruction Backdoor Attacks Against Cutomized LLMs

pdf arxiv code

Prompt Stealing Attacks Against Text-to-Image Generation Models

pdf arxiv code dataset

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

pdf arxiv code

Quantifying Privacy Risks of Prompts in Visual Prompt Learning

pdf arxiv code

Link Stealing Attacks Against Inductive Graph Neural Networks

pdf arxiv code

Composite Backdoor Attacks Against Large Language Models

pdf arxiv code

Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming

pdf arxiv code

FAKEPCD: Fake Point Cloud Detection via Source Attribution

pdf arxiv code

You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content

pdf arxiv code

Test-Time Poisoning Attacks Against Test-Time Adaptation Models

pdf arxiv code

Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models

pdf arxiv code

VERITRAIN: Validating MLaaS Training Efforts via Anomaly Detection

pdf

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

arxiv

On the Generalization Ability of Machine-Generated Text Detectors

arxiv

Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification

arxiv

ICLGuard: Controlling In-Context Learning Behavior for Applicability Authorization

arxiv

SOS! Soft Prompt Attack Against Open-Source Large Language Models

arxiv

Voice Jailbreak Attacks Against GPT-4o

arxiv

UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images

arxiv

VGMShield: Mitigating Misuse of Video Generative Models

arxiv

Prompt Stealing Attacks Against Large Language Models

arxiv

2023

DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models

pdf arxiv code

Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models

pdf arxiv code

Differentially Private Resource Allocation

pdf

A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots

pdf arxiv code

Two-in-One: A Model Hijacking Attack Against Text Generation Models

pdf arxiv

UnGANable: Defending Against GAN-based Face Manipulation

pdf arxiv code Media Coverage: Mimikama, it-sicherheit.de, SOLARIFY, elektroniknet.de, Digitale Schweiz, innovations report

FACE-AUDITOR: Data Auditing in Facial Recognition Systems

pdf arxiv

PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model

pdf arxiv

Generated Graph Detection

pdf arxiv code

Data Poisoning Attacks Against Multimodal Encoders

pdf arxiv code

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models

pdf arxiv code

Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders

pdf arxiv code

On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning

pdf arxiv code

Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?

pdf code

Backdoor Attacks Against Dataset Distillation

pdf arxiv code

Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network

pdf arxiv code

Comprehensive Assessment of Toxicity in ChatGPT

arxiv

Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning

arxiv

Prompt Backdoors in Visual Prompt Learning

arxiv

Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models

arxiv

Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing

arxiv

Watermarking Diffusion Model

arxiv

In ChatGPT We Trust? Measuring and Characterizing the Reliability of ChatGPT

arxiv

Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis

arxiv

2022

Amplifying Membership Exposure via Data Poisoning

pdf arxiv code

Why So Toxic?: Measuring and Triggering Toxic Behavior in Open-Domain Chatbots

pdf arxiv Media Coverage: Fast Company
Best Paper Award Honorable Mention

On the Privacy Risks of Cell-Based NAS Architectures

pdf arxiv code

Membership Inference Attacks by Exploiting Loss Trajectory

pdf arxiv code

Auditing Membership Leakages of Multi-Exit Networks

pdf arxiv code

Graph Unlearning

pdf arxiv

SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders

pdf arxiv code

Finding MNEMON: Reviving Memories of Node Embeddings

pdf arxiv

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

pdf arxiv code

Teacher Model Fingerprinting Attacks Against Transfer Learning

pdf arxiv code

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

pdf arxiv code

Inference Attacks Against Graph Neural Networks

pdf arxiv

On Xing Tian and the Perseverance of Anti-China Sentiment Online

pdf arxiv

Model Stealing Attacks Against Inductive Graph Neural Networks

pdf arxiv code

Get a Model! Model Hijacking Attack Against Machine Learning Models

pdf arxiv code

Property Inference Attacks Against GANs

pdf arxiv code

Dynamic Backdoor Attacks Against Machine Learning Models

pdf arxiv code

FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings

pdf arxiv

Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

arxiv

Membership Inference Attacks Against Text-to-image Generation Models

arxiv

Backdoor Attacks in the Supply Chain of Masked Image Modeling

arxiv

Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models

arxiv

2021

Quantifying and Mitigating Privacy Risks of Contrastive Learning

pdf arxiv code

When Machine Unlearning Jeopardizes Privacy

pdf arxiv

Membership Inference Attacks Against Recommender Systems

pdf arxiv code

Membership Leakage in Label-Only Exposures

pdf arxiv code

BadNL: Backdoor Attacks Against NLP Models with Semantic-preserving Improvements

pdf arxiv

Stealing Links from Graph Neural Networks

pdf arxiv code

PrivSyn: Differentially Private Data Synthesis

pdf arxiv

“Go eat a bat, Chang!”: On the Emergence of Sinophobic Behavior on Web Communities in the Face of COVID-19

pdf arxiv Media Coverage: The Washington Post

DatingSec: Detecting Malicious Accounts in Dating Apps Using a Content-Based Attention Network

pdf

Node-Level Membership Inference Attacks Against Graph Neural Networks

arxiv

2020

LEAF: A Faster Secure Search Algorithm via Localization, Extraction, and Reconstruction

pdf

GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models

pdf arxiv code

Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning

pdf arxiv code

Membership Inference Against DNA Methylation Databases

pdf

Towards Plausible Graph Anonymization

pdf arxiv

Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks

arxiv

BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models

arxiv

Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning

arxiv

2019

MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

pdf arxiv code

How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNN

pdf

A Graph-Based Approach to Explore Relationship Between Hashtags and Images

pdf

Fairwalk: Towards Fair Graph Embedding

pdf code

Language in Our Time: An Empirical Analysis of Hashtags

pdf arxiv

ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models

pdf arxiv code

MBeacon: Privacy-Preserving Beacons for DNA Methylation Data

pdf
Distinguished Paper Award

2018

You Are Where You APP: An Assessment on Location Privacy of Social APPs

pdf

Tagvisor: A Privacy Advisor for Sharing Hashtags

pdf arxiv

Dissecting Privacy Risks in Biomedical Data

pdf

An Active Learning-based Approach for Location-aware Acquaintance Inference

pdf

2017

walk2friends: Inferring Social Links from Mobility Profiles

pdf arxiv code

Semantic Annotation for Places in LBSN Using Graph Embedding

pdf

Does #like4like Indeed Provoke More Likes?

pdf

Quantifying Location Sociality

pdf arxiv

DeepCity: A Feature Learning Framework for Mining Location Check-ins

pdf arxiv

2016

On Impact of Weather on Human Mobility in Cities

pdf

An Empirical Study on User Access Control in Online Social Networks

pdf

2015

Location Prediction: Communities Speak Louder than Friends

pdf arxiv

Distance and Friendship: A Distance-based Model for Link Prediction in Social Networks

pdf

Event Prediction with Community Leaders

pdf

A Logical Approach for Blocking Access in Social Networks

pdf

Cryptographic Protocols for Enforcing Topology-based Access Control Policies

pdf

A New Access Control Scheme for Facebook-style Social Networks

pdf arxiv

Exploring Communities for Effective Location Predication

pdf

Community-driven Social Influence Analysis and Applications

pdf

2014

A New Access Control Scheme for Facebook-style Social Networks

pdf
Best Paper Award