Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
OutSafe-Bench: A Benchmark for Multimodal Offensive Content Detection in Large Language Models
Yuping Yan, Yuhan Xie, Yuanshuai Li +3
Since Multimodal Large Language Models (MLLMs) are increasingly being integrated into everyday tools and intelligent agents, growing concerns have arisen regarding their possible o…
cs.LG2025
Exploit Gradient Skewness to Circumvent Byzantine Defenses for Federated Learning
Yuchen Liu, Chen Chen, Lingjuan Lyu +2
Federated Learning (FL) is notorious for its vulnerability to Byzantine attacks. Most current Byzantine defenses share a common inductive bias: among all the gradients, the densely…