32 citations · 109 across the 12 of their papers we have counts for
12 papers
Benchmarking the Benchmarks: Evaluating Automated Safety Benchmarks for Small Language Models
Nyamtulla Shaik, Fengjun Li, Bo Luo
Small Language Models (SLMs) are increasingly deployed in resource-constrained, privacy-sensitive settings, where safety and bias failures can cause security and societal risks. Ho…
PhantomSeal: Proactive Deepfakes Defense with Identity/Context Protection and Forensic Tracing
Liangqin Ren, Zeyan Liu, Ye Wang +3
Deepfakes, especially face-swapping attacks, pose significant challenges to authenticity, security, and ethics across science, engineering, and society. While most existing detecti…
PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption
Liangqin Ren, Zeyan Liu, Fengjun Li +3
In the past decade, we have witnessed an exponential growth of deep learning models, platforms, and applications. While existing DL applications and Machine Learning as a service (…
The Adversarial AI-Art: Understanding, Generation, Detection, and Benchmarking
Yuying Li, Zeyan Liu, Junyi Zhao +4
Generative AI models can produce high-quality images based on text prompts. The generated images often appear indistinguishable from images generated by conventional optical photog…
Multi-Layer Dense Attention Decoder for Polyp Segmentation
Krushi Patel, Fengjun Li, Guanghui Wang
Detecting and segmenting polyps is crucial for expediting the diagnosis of colon cancer. This is a challenging task due to the large variations of polyps in color, texture, and lig…
On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing
Zeyan Liu, Zijun Yao, Fengjun Li +1
With ChatGPT under the spotlight, utilizing large language models (LLMs) to assist academic writing has drawn a significant amount of debate in the community. In this paper, we aim…
Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems
Zeyan Liu, Fengjun Li, Jingqiang Lin +2
With the growing popularity of artificial intelligence and machine learning, a wide spectrum of attacks against deep learning models have been proposed in the literature. Both the…
AFL: Non-intrusive Feedback-driven Fuzzing for Microcontroller Firmware
Wenqiang Li, Jiameng Shi, Fengjun Li +3
Fuzzing is one of the most effective approaches to finding software flaws. However, applying it to microcontroller firmware incurs many challenges. For example, rehosting-based sol…
Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency
Sohaib Kiani, Sana Awan, Chao Lan +2
In the evasion attacks against deep neural networks (DNN), the attacker generates adversarial instances that are visually indistinguishable from benign samples and sends them to th…
UPPRESSO: Untraceable and Unlinkable Privacy-PREserving Single Sign-On Services
Chengqian Guo, Jingqiang Lin, Quanwei Cai +6
Single sign-on (SSO) allows a user to maintain only the credential for an identity provider (IdP) to log into multiple relying parties (RPs). However, SSO introduces privacy threat…
From Library Portability to Para-rehosting: Natively Executing Microcontroller Software on Commodity Hardware
Wenqiang Li, Le Guan, Jingqiang Lin +2
Finding bugs in microcontroller (MCU) firmware is challenging, even for device manufacturers who own the source code. The MCU runs different instruction sets than x86 and exposes a…
Cyber-Physical Systems Security -- A Survey
Abdulmalik Humayed, Jingqiang Lin, Fengjun Li +1
With the exponential growth of cyber-physical systems (CPS), new security challenges have emerged. Various vulnerabilities, threats, attacks, and controls have been introduced for…