16 citations · 42 across the 13 of their papers we have counts for
13 papers
SyncGait: Robust Long-Distance Authentication for Drone Delivery via Implicit Gait Behaviors
Zijian Ling, Man Zhou, Hongda Zhai +5
In recent years, drone delivery, which utilizes unmanned aerial vehicles (UAVs) for package delivery and pickup, has gradually emerged as a crucial method in logistics. Since deliv…
JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
Shenyi Zhang, Yuchen Zhai, Keyan Guo +7
Despite the implementation of safety alignment strategies, large language models (LLMs) remain vulnerable to jailbreak attacks, which undermine these safety guardrails and pose sig…
Solid-SQL: Enhanced Schema-linking based In-context Learning for Robust Text-to-SQL
Geling Liu, Yunzhi Tan, Ruichao Zhong +5
Recently, large language models (LLMs) have significantly improved the performance of text-to-SQL systems. Nevertheless, many state-of-the-art (SOTA) approaches have overlooked the…
Advancing Video Quality Assessment for AIGC
Xinli Yue, Jianhui Sun, Han Kong +9
In recent years, AI generative models have made remarkable progress across various domains, including text generation, image generation, and video generation. However, assessing th…
Revisiting Video Quality Assessment from the Perspective of Generalization
Xinli Yue, Jianhui Sun, Liangchao Yao +8
The increasing popularity of short video platforms such as YouTube Shorts, TikTok, and Kwai has led to a surge in User-Generated Content (UGC), which presents significant challenge…
Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
Zheng Fang, Tao Wang, Lingchen Zhao +6
In recent years, extensive research has been conducted on the vulnerability of ASR systems, revealing that black-box adversarial example attacks pose significant threats to real-wo…
Boosting Adversarial Transferability with Low-Cost Optimization via Maximin Expected Flatness
Chunlin Qiu, Ang Li, Yiheng Duan +4
Transfer-based attacks craft adversarial examples on white-box surrogate models and directly deploy them against black-box target models, offering model-agnostic and query-free thr…
Revisiting Adversarial Training under Long-Tailed Distributions
Xinli Yue, Ningping Mou, Qian Wang +1
Deep neural networks are vulnerable to adversarial attacks, often leading to erroneous outputs. Adversarial training has been recognized as one of the most effective methods to cou…
Hijacking Attacks against Neural Networks by Analyzing Training Data
Yunjie Ge, Qian Wang, Huayang Huang +7
Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended ou…
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
JiaCheng Deng, Li Dong, Jiahao Chen +5
Optical Character Recognition (OCR) enables automatic text extraction from scanned or digitized text images, but it also makes it easy to pirate valuable or sensitive text from the…
Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection
Lingchen Zhao, Shengshan Hu, Qian Wang +4
Collaborative learning allows multiple clients to train a joint model without sharing their data with each other. Each client performs training locally and then submits the model u…
VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a Service
Lingchen Zhao, Qian Wang, Cong Wang +5
Machine Learning as a Service (MLaaS) allows clients with limited resources to outsource their expensive ML tasks to powerful servers. Despite the huge benefits, current MLaaS solu…
Privacy-Preserving Collaborative Deep Learning with Unreliable Participants
Lingchen Zhao, Qian Wang, Qin Zou +2
With powerful parallel computing GPUs and massive user data, neural-network-based deep learning can well exert its strong power in problem modeling and solving, and has archived gr…