4 papers · 1 filter
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…
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…
ParetoHqD: Fast Offline Multiobjective Alignment of Large Language Models using Pareto High-quality Data
Haoran Gu, Handing Wang, Yi Mei +2
Aligning large language models with multiple human expectations and values is crucial for ensuring that they adequately serve a variety of user needs. To this end, offline multiobj…
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…