14 citations · 19 across the 13 of their papers we have counts for
13 papers
Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents
Jiawei Liu, Jiacheng Guo, Tian Zhang +7
Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making planner-visible st…
MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration
Shenyi Zhang, Keyan Guo, Zihao Wang +5
Multimodal large language models (MLLMs) often refuse unsafe text prompts yet generate harmful responses to semantically equivalent multimodal inputs. Existing defenses either rely…
SoK: AI Secure Code Generation: Progress, Pitfalls, and Paths Forward
Rupam Patir, Keyan Guo, Haipeng Cai +1
The increasing use of AI systems for code generation raises a central security question: what can today's models and coding agents actually do to produce secure code, where do they…
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
Safayat Bin Hakim, Keyan Guo, Wenkai Tan +3
LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, an…
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Tian Zhang, Yiwei Xu, Juan Wang +8
Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. Thi…
DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents
Rupam Patir, Keyan Guo, Suvadra Barua +5
Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functionally correct and…
Fortifying LLM-Based Code Generation with Graph-Based Reasoning on Secure Coding Practices
Rupam Patir, Keyan Guo, Haipeng Cai +1
The code generation capabilities of Large Language Models (LLMs) have transformed the field of software development. However, this advancement also presents significant security ch…
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…
AI-Cybersecurity Education Through Designing AI-based Cyberharassment Detection Lab
Ebuka Okpala, Nishant Vishwamitra, Keyan Guo +7
Cyberharassment is a critical, socially relevant cybersecurity problem because of the adverse effects it can have on targeted groups or individuals. While progress has been made in…
Moderating Embodied Cyber Threats Using Generative AI
Keyan Guo, Freeman Guo, Hongxin Hu
The advancement in computing and hardware, like spatial computing and VR headsets (e.g., Apple's Vision Pro) [1], has boosted the popularity of social VR platforms (VRChat, Rec Roo…
Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models
Keyan Guo, Ayush Utkarsh, Wenbo Ding +5
Online user generated content games (UGCGs) are increasingly popular among children and adolescents for social interaction and more creative online entertainment. However, they pos…
An Investigation of Large Language Models for Real-World Hate Speech Detection
Keyan Guo, Alexander Hu, Jaden Mu +4
Hate speech has emerged as a major problem plaguing our social spaces today. While there have been significant efforts to address this problem, existing methods are still significa…
Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models
Nishant Vishwamitra, Keyan Guo, Farhan Tajwar Romit +4
Online hate is an escalating problem that negatively impacts the lives of Internet users, and is also subject to rapid changes due to evolving events, resulting in new waves of onl…