11 citations · 21 across the 13 of their papers we have counts for
17 papers
Same Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety Classifiers
Xiang Li, Aichun Huang, Mingming Zhang +1
TypeSafe AI's Jev is a new kind of safety judge. It generates no text and no label: it answers questions the developer defines in advance and returns a probability for each answer.…
When Talk Isn't Code: Comparing LLM Agents That Simulate and Develop Software
Xiang Li, Aichun Huang, Mingming Zhang +1
LLMs are used both to simulate network protocol implementations, as honeypots do, and to write them. Prior work evaluates the two uses separately, from a model's answers or convers…
One Is Not Enough: The Untold Story of Multiple Security Patches for One Vulnerability
Fangyuan Zhang, Lyuye Zhang, Lingling Fan +6
Security patches (SPs) are the main mechanism for fixing software vulnerabilities, yet a single vulnerability is not always resolved by a single patch: fixes may be completed incre…
KubeCap: A Framework for Capability Minimization in Kubernetes via Static Analysis and LLM-Assisted Rule Inference
Yuhao Liu, Yingnan Zhou, Weijie Liu +2
As the most widely used container orchestration platform, Kubernetes provides flexible privilege configuration by allowing developers to manage Linux capabilities via manifest file…
ColluSkill: Adversarial Cross-Skill Composition for Evading Agent Skill Scanners
Puyu Zeng, Simeng Qin, Jingzhi Li +3
Agent skills are emerging as an important attack surface in LLM-based agent systems. Through an empirical study of existing skill scanners, we find that current defenses mainly ins…
Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories
Jianing Geng, Ruiqi He, Zekun Fei +6
Agent skills package reusable procedures that improve downstream performance. Their lightweight, portable form enables marketplace monetization and private deployment behind cloud-…
Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs
Zekun Fei, Zihao Wang, Weijie Liu +4
Mixture-of-Experts (MoE) architectures have emerged as a leading paradigm for scaling large language models through sparse, routing-based computation. However, this design introduc…
Not All Entities are Created Equal: A Dynamic Anonymization Framework for Privacy-Preserving RAG
Xinyuan Zhu, Zekun Fei, Enye Wang +5
Retrieval-Augmented Generation (RAG) enhances the utility of Large Language Models (LLMs) by retrieving external documents. Since the knowledge databases in RAG are predominantly u…
Rethinking Software Misconfigurations in the Real World: An Empirical Study and Literature Analysis
Yuhao Liu, Yingnan Zhou, Hanfeng Zhang +6
Software misconfiguration has consistently been a major reason for software failures. Over the past two decades, much work has been done to detect and diagnose software misconfigur…
BadActs: A Universal Backdoor Defense in the Activation Space
Biao Yi, Sishuo Chen, Yiming Li +3
Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage. In response, backdoor sample purification has emerged as…
LAN: Learning Adaptive Neighbors for Real-Time Insider Threat Detection
Xiangrui Cai, Yang Wang, Sihan Xu +4
Enterprises and organizations are faced with potential threats from insider employees that may lead to serious consequences. Previous studies on insider threat detection (ITD) main…
Analyzing Consumer IoT Traffic from Security and Privacy Perspectives: a Comprehensive Survey
Yan Jia, Yuxin Song, Zihou Liu +4
The Consumer Internet of Things (CIoT), a notable segment within the IoT domain, involves the integration of IoT technology into consumer electronics and devices, such as smart hom…
LiSum: Open Source Software License Summarization with Multi-Task Learning
Linyu Li, Sihan Xu, Yang Liu +5
Open source software (OSS) licenses regulate the conditions under which users can reuse, modify, and distribute the software legally. However, there exist various OSS licenses in t…
LiResolver: License Incompatibility Resolution for Open Source Software
Sihan Xu, Ya Gao, Lingling Fan +3
Open source software (OSS) licenses regulate the conditions under which OSS can be legally reused, distributed, and modified. However, a common issue arises when incorporating thir…
New Differential Privacy Communication Pipeline and Design Framework
Jingyu Jia, Zikai Alex Wen, Zheli Liu +1
Organizations started to adopt differential privacy (DP) techniques hoping to persuade more users to share personal data with them. However, many users do not understand DP techniq…
LiDetector: License Incompatibility Detection for Open Source Software
Sihan Xu, Ya Gao, Lingling Fan +3
Open-source software (OSS) licenses dictate the conditions which should be followed to reuse, distribute, and modify the software. Apart from widely-used licenses such as the MIT L…
RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE
Yali Yuan, Robert Tasik, Sripriya Srikant Adhatarao +3
With the rapid development of autonomous driving, collision avoidance has attracted attention from both academia and industry. Many collision avoidance strategies have emerged in r…