1 citations · 1 across the 7 of their papers we have counts for
7 papers
SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar +1
The ability of LLM agents to plan and invoke tools exposes them to new safety risks, making a comprehensive red-teaming system crucial for discovering vulnerabilities and ensuring…
SEASONED: Semantic-Enhanced Self-Counterfactual Explainable Detection of Adversarial Exploiter Contracts
Xng Ai, Shudan Lin, Zecheng Li +3
Decentralized Finance (DeFi) attacks have resulted in significant losses, often orchestrated through Adversarial Exploiter Contracts (AECs) that exploit vulnerabilities in victim s…
Multi-Grained Temporal-Spatial Graph Learning for Stable Traffic Flow Forecasting
Zhenan Lin, Yuni Lai, Wai Lun Lo +5
Time-evolving traffic flow forecasting are playing a vital role in intelligent transportation systems and smart cities. However, the dynamic traffic flow forecasting is a highly no…
Defense-as-a-Service: Black-box Shielding against Backdoored Graph Models
Xiao Yang, Kai Zhou, Yuni Lai +1
With the trend of large graph learning models, business owners tend to employ a model provided by a third party to deliver business services to users. However, these models might b…
Collective Certified Robustness against Graph Injection Attacks
Yuni Lai, Bailin Pan, Kaihuang Chen +2
We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading t…
Cost Aware Untargeted Poisoning Attack against Graph Neural Networks,
Yuwei Han, Yuni Lai, Yulin Zhu +1
Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts h…
Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attacks
Yuni Lai, Yulin Zhu, Bailin Pan +1
Deep Graph Learning (DGL) has emerged as a crucial technique across various domains. However, recent studies have exposed vulnerabilities in DGL models, such as susceptibility to e…