143 citations · 299 across the 23 of their papers we have counts for
23 papers
Test-Time Poisoning Attacks Against Test-Time Adaptation Models
Tianshuo Cong, Xinlei He, Yun Shen +1
Deploying machine learning (ML) models in the wild is challenging as it suffers from distribution shifts, where the model trained on an original domain cannot generalize well to un…
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Xinlei He, Savvas Zannettou, Yun Shen +1
The spread of toxic content online is an important problem that has adverse effects on user experience online and in our society at large. Motivated by the importance and impact of…
Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models
Yugeng Liu, Tianshuo Cong, Zhengyu Zhao +3
Large Language Models (LLMs) undergo continuous updates to improve user experience. However, prior research on the security and safety implications of LLMs has primarily focused on…
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
Xinyue Shen, Zeyuan Chen, Michael Backes +2
The misuse of large language models (LLMs) has drawn significant attention from the general public and LLM vendors. One particular type of adversarial prompt, known as jailbreak pr…
Generated Graph Detection
Yihan Ma, Zhikun Zhang, Ning Yu +4
Graph generative models become increasingly effective for data distribution approximation and data augmentation. While they have aroused public concerns about their malicious misus…
Watermarking Diffusion Model
Yugeng Liu, Zheng Li, Michael Backes +2
The availability and accessibility of diffusion models (DMs) have significantly increased in recent years, making them a popular tool for analyzing and predicting the spread of inf…
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Boyang Zhang, Xinlei He, Yun Shen +2
Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates t…
One Size Does not Fit All: Quantifying the Risk of Malicious App Encounters for Different Android User Profiles
Savino Dambra, Leyla Bilge, Platon Kotzias +2
Previous work has investigated the particularities of security practices within specific user communities defined based on country of origin, age, prior tech abuse, and economic st…
Backdoor Attacks Against Dataset Distillation
Yugeng Liu, Zheng Li, Michael Backes +2
Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into…
Amplifying Membership Exposure via Data Poisoning
Yufei Chen, Chao Shen, Yun Shen +2
As in-the-wild data are increasingly involved in the training stage, machine learning applications become more susceptible to data poisoning attacks. Such attacks typically lead to…
Backdoor Attacks in the Supply Chain of Masked Image Modeling
Xinyue Shen, Xinlei He, Zheng Li +3
Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive lear…
Cerberus: Exploring Federated Prediction of Security Events
Mohammad Naseri, Yufei Han, Enrico Mariconti +3
Modern defenses against cyberattacks increasingly rely on proactive approaches, e.g., to predict the adversary's next actions based on past events. Building accurate prediction mod…
On the Privacy Risks of Cell-Based NAS Architectures
Hai Huang, Zhikun Zhang, Yun Shen +3
Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance. Little progress has be…
Finding MNEMON: Reviving Memories of Node Embeddings
Yun Shen, Yufei Han, Zhikun Zhang +5
Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of g…
A Large-scale Temporal Measurement of Android Malicious Apps: Persistence, Migration, and Lessons Learned
Yun Shen, Pierre-Antoine Vervier, Gianluca Stringhini
We study the temporal dynamics of potentially harmful apps (PHAs) on Android by leveraging 8.8M daily on-device detections collected among 11.7M customers of a popular mobile secur…
Marked for Disruption: Tracing the Evolution of Malware Delivery Operations Targeted for Takedown
Colin C. Ife, Yun Shen, Steven J. Murdoch +1
The malware and botnet phenomenon is among the most significant threats to cybersecurity today. Consequently, law enforcement agencies, security companies, and researchers are cons…
ANDRUSPEX : Leveraging Graph Representation Learning to Predict Harmful App Installations on Mobile Devices
Yun Shen, Gianluca Stringhini
Android's security model severely limits the capabilities of anti-malware software. Unlike commodity anti-malware solutions on desktop systems, their Android counterparts run as sa…
Understanding Worldwide Private Information Collection on Android
Yun Shen, Pierre-Antoine Vervier, Gianluca Stringhini
Mobile phones enable the collection of a wealth of private information, from unique identifiers (e.g., email addresses), to a user's location, to their text messages. This informat…
Node-Level Membership Inference Attacks Against Graph Neural Networks
Xinlei He, Rui Wen, Yixin Wu +3
Many real-world data comes in the form of graphs, such as social networks and protein structure. To fully utilize the information contained in graph data, a new family of machine l…
ATTACK2VEC: Leveraging Temporal Word Embeddings to Understand the Evolution of Cyberattacks
Yun Shen, Gianluca Stringhini
Despite the fact that cyberattacks are constantly growing in complexity, the research community still lacks effective tools to easily monitor and understand them. In particular, th…
Tiresias: Predicting Security Events Through Deep Learning
Yun Shen, Enrico Mariconti, Pierre-Antoine Vervier +1
With the increased complexity of modern computer attacks, there is a need for defenders not only to detect malicious activity as it happens, but also to predict the specific steps…
Collaborative and Privacy-Preserving Machine Teaching via Consensus Optimization
Yufei Han, Yuzhe Ma, Christopher Gates +2
In this work, we define a collaborative and privacy-preserving machine teaching paradigm with multiple distributed teachers. We focus on consensus super teaching. It aims at organi…
Mini-Batch Spectral Clustering
Yufei Han, Maurizio Filippone
The cost of computing the spectrum of Laplacian matrices hinders the application of spectral clustering to large data sets. While approximations recover computational tractability,…