1 citations · 2 across the 8 of their papers we have counts for
10 papers
Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition
Dianshu Liao, Shidong Pan, Guangdong Bai +2
Agent skills extend the capabilities of AI agents by bundling instructions, code, and resources into reusable packages. During skill execution, agents may produce or modify artifac…
Continuous Assurance of Agentic Security Auditors for Software Delivery Decision Gates
Guy Lupo, Nguyen Hung Nguyen, Viet Vo +4
Large language model (LLM)-based repository auditors are increasingly deployed as security controls within continuous integration (CI) pipelines, where their findings admit, block,…
A Comprehensive Study of Implementation Bugs in Multi-modal Agents
Suwan Li, Lei Bu, Shangqing Liu +5
Multi-Modal Agents (M-agents), empowered by Large Language Models (LLMs), excel in various complex, open-world scenarios such as autonomous driving and robotics. However, their uni…
Detecting Manipulated Contents Using Knowledge-Grounded Inference
Mark Huasong Meng, Ruizhe Wang, Meng Xu +2
The detection of manipulated content, a prevalent form of fake news, has been widely studied in recent years. While existing solutions have been proven effective in fact-checking a…
Detecting Multi-Parameter Constraint Inconsistencies in Python Data Science Libraries
Xiufeng Xu, Fuman Xie, Chenguang Zhu +3
Modern AI- and Data-intensive software systems rely heavily on data science and machine learning libraries that provide essential algorithmic implementations and computational fram…
Exploring ChatGPT App Ecosystem: Distribution, Deployment and Security
Chuan Yan, Ruomai Ren, Mark Huasong Meng +3
ChatGPT has enabled third-party developers to create plugins to expand ChatGPT's capabilities.These plugins are distributed through OpenAI's plugin store, making them easily access…
Model-Enhanced LLM-Driven VUI Testing of VPA Apps
Suwan Li, Lei Bu, Guangdong Bai +3
The flourishing ecosystem centered around voice personal assistants (VPA), such as Amazon Alexa, has led to the booming of VPA apps. The largest app market Amazon skills store, for…
Universal Adversarial Perturbations for Vision-Language Pre-trained Models
Peng-Fei Zhang, Zi Huang, Guangdong Bai
Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robus…
Effective and Robust Adversarial Training against Data and Label Corruptions
Peng-Fei Zhang, Zi Huang, Xin-Shun Xu +1
Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing eff…
PAODING: A High-fidelity Data-free Pruning Toolkit for Debloating Pre-trained Neural Networks
Mark Huasong Meng, Hao Guan, Liuhuo Wan +3
We present PAODING, a toolkit to debloat pretrained neural network models through the lens of data-free pruning. To preserve the model fidelity, PAODING adopts an iterative process…