133 citations · 465 across the 67 of their papers we have counts for
68 papers
Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond
Nivedita Singh, Alsharif Abuadbba, Yansong Gao +2
Large language models (LLMs) are becoming integral to web applications and browser agents, transforming online interactions while introducing new attack vectors and reshaping longs…
JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving
Tairui Wang, Zhi Zhang, Yansong Gao +3
LLMs are widely deployed through cloud-hosted inference services, where Just-in-Time (JIT) compilation is used to reduce recurring framework and GPU-launch overhead. JIT serving in…
DisCTI: Who Needs to Know Timely? Automated Sector-Aware Cyber Threat Intelligence Dissemination
Fajar Wijitrisnanto, Alsharif Abuadbba, Yansong Gao +1
The timely dissemination of cyber threat intelligence (CTI) is critical for organizations to mount swift and effective incident response. When valid CTI is delivered to the right s…
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
Na Li, Boyu Kuang, Hongsheng Hu +4
To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image…
From Multiplicity to Vulnerability: Privacy Amplification Risk from One-Dataset-Multiple-Model Exposure
Qirui Huang, Na Li, Hongsheng Hu +3
To efficiently exploit a valuable data source (e.g., facial or medical images), it is frequently harnessed to fulfill multiple learning objectives (e.g., facial recognition, age es…
CausShield: Sample Reconstruction-Resilient Vertical FL via Causal Representation Learning
Yongqi Jiang, Yansong Gao, Siguang Chen +1
Vertical federated learning (VFL) is a distributed learning paradigm that leverages vertically partitioned features across isolated parties without sharing raw samples; however, it…
From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints
Yansong Gao, Huaibing Peng, Hua Ma +5
For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all…
Intellectual Property Protection for Deep Learning Model and Dataset Intelligence
Yongqi Jiang, Yansong Gao, Chunyi Zhou +3
With the growing applications of Deep Learning (DL), especially recent spectacular achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the commercial significan…
DeepiSign-G: Generic Watermark to Stamp Hidden DNN Parameters for Self-contained Tracking
Alsharif Abuadbba, Nicholas Rhodes, Kristen Moore +3
Deep learning solutions in critical domains like autonomous vehicles, facial recognition, and sentiment analysis require caution due to the severe consequences of errors. Research…
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
Shengfang Zhai, Huanran Chen, Yinpeng Dong +5
Text-to-image diffusion models have achieved tremendous success in the field of controllable image generation, while also coming along with issues of privacy leakage and data copyr…
Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
Na Li, Chunyi Zhou, Yansong Gao +4
Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the right to be f…
ObliuSky: Oblivious User-Defined Skyline Query Processing in the Cloud
Yifeng Zheng, Weibo Wang, Songlei Wang +2
The proliferation of cloud computing has greatly spurred the popularity of outsourced database storage and management, in which the cloud holding outsourced databases can process d…
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
Hua Ma, Shang Wang, Yansong Gao +7
All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class act…
DeepTheft: Stealing DNN Model Architectures through Power Side Channel
Yansong Gao, Huming Qiu, Zhi Zhang +6
Deep Neural Network (DNN) models are often deployed in resource-sharing clouds as Machine Learning as a Service (MLaaS) to provide inference services.To steal model architectures t…
One-to-Multiple Clean-Label Image Camouflage (OmClic) based Backdoor Attack on Deep Learning
Guohong Wang, Hua Ma, Yansong Gao +6
Image camouflage has been utilized to create clean-label poisoned images for implanting backdoor into a DL model. But there exists a crucial limitation that one attack/poisoned ima…
Alert-ME: An Explainability-Driven Defense Against Adversarial Examples in Transformer-Based Text Classification
Bushra Sabir, Yansong Gao, Alsharif Abuadbba +1
Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial exampl…
Privet: A Privacy-Preserving Vertical Federated Learning Service for Gradient Boosted Decision Tables
Yifeng Zheng, Shuangqing Xu, Songlei Wang +2
Vertical federated learning (VFL) has recently emerged as an appealing distributed paradigm empowering multi-party collaboration for training high-quality models over vertically pa…
Fast Diffusion Probabilistic Model Sampling through the lens of Backward Error Analysis
Yansong Gao, Zhihong Pan, Xin Zhou +2
Denoising diffusion probabilistic models (DDPMs) are a class of powerful generative models. The past few years have witnessed the great success of DDPMs in generating high-fidelity…
On the Use of Power Amplifier Nonlinearity Quotient to Improve Radio Frequency Fingerprint Identification in Time-Varying Channels
Lu Yang, Seyit Camtepe, Yansong Gao +2
Radio frequency fingerprint identification (RFFI) is a lightweight device authentication technique particularly desirable for power-constrained devices, e.g., the Internet of thing…
Vertical Federated Learning: Taxonomies, Threats, and Prospects
Qun Li, Chandra Thapa, Lawrence Ong +5
Federated learning (FL) is the most popular distributed machine learning technique. FL allows machine-learning models to be trained without acquiring raw data to a single point for…
Imperceptible Sample-Specific Backdoor to DNN with Denoising Autoencoder
Xiangqi Wang, Mingfu Xue, Kewei Chen +4
The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which…
Split Learning without Local Weight Sharing to Enhance Client-side Data Privacy
Ngoc Duy Pham, Tran Khoa Phan, Alsharif Abuadbba +3
Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. In SL training with multiple clients, the…
DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks
Seonhye Park, Alsharif Abuadbba, Shuo Wang +4
Training deep neural networks (DNNs) requires large datasets and powerful computing resources, which has led some owners to restrict redistribution without permission. Watermarking…
TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World
Hua Ma, Yinshan Li, Yansong Gao +6
Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfacto…