Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction
Zhaoxin Wang, Handing Wang, Cong Tian +1
Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attac…
cs.LG2025
Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
Zhaoxin Wang, Handing Wang, Cong Tian +1
Multimodal large language models (MLLMs) enable powerful cross-modal reasoning capabilities. However, the expanded input space introduces new attack surfaces. Previous jailbreak at…
cs.LG2024
Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
Zhaoxin Wang, Handing Wang, Cong Tian +1
Adversarial training (AT) has become an effective defense method against adversarial examples (AEs) and it is typically framed as a bi-level optimization problem. Among various AT…