activity
20242026
most citedAI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways

184 citations · 187 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CR2026

Beyond Her: Safety Dynamics in Role-play AI Companions

Zehang Deng, Zhaoyang Xie, Changzhou Han +8

The film 'Her' pictured a future of love between humans and AI. That future has quietly emerged in the form of Role-play AI Companions (RACs), where emotionally responsive interact…

cs.LG2026

Sharpness-Aware Minimization in Logit Space Efficiently Enhances Direct Preference Optimization

Haocheng Luo, Zehang Deng, Thanh-Toan Do +3

Direct Preference Optimization (DPO) has emerged as a popular algorithm for aligning pretrained large language models with human preferences, owing to its simplicity and training s…

cs.CV2026

Decoupling Defense Strategies for Robust Image Watermarking

Jiahui Chen, Zehang Deng, Zeyu Zhang +3

Deep learning-based image watermarking, while robust against conventional distortions, remains vulnerable to advanced adversarial and regeneration attacks. Conventional countermeas…

cs.CR2025★ 1 cited

MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security

Yongjian Guo, Puzhuo Liu, Wanlun Ma +5

The Model Context Protocol (MCP) has emerged as a universal standard that enables AI agents to seamlessly connect with external tools, significantly enhancing their functionality.…

cs.CV2024★ 2 cited

GRFormer: Grouped Residual Self-Attention for Lightweight Single Image Super-Resolution

Yuzhen Li, Zehang Deng, Yuxin Cao +1

Previous works have shown that reducing parameter overhead and computations for transformer-based single image super-resolution (SISR) models (e.g., SwinIR) usually leads to a redu…

cs.CR2024★ 184 cited

AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways

Zehang Deng, Yongjian Guo, Changzhou Han +4

An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable o…

cs.CR2024

Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure

Zehang Deng, Ruoxi Sun, Minhui Xue +4

AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of soci…