4 papers
Breaking the Secret: Economic Interventions for Combating Collusion in Embodied Multi-Agent Systems
Qi Liu, Xiaohui Chen, Zhihui Zhao +5
Collusion among autonomous agents poses a critical security threat in embodied multi-agent systems (MAS), where coordinated behaviors can deviate from global objectives and lead to…
SMTFL: Secure Model Training to Untrusted Participants in Federated Learning
Zhihui Zhao, Xiaorong Dong, Yimo Ren +4
Federated learning is an essential distributed model training technique. However, threats such as gradient inversion attacks and poisoning attacks pose significant risks to the pri…
PipeOptim: Ensuring Effective 1F1B Schedule with Optimizer-Dependent Weight Prediction
Lei Guan, Dongsheng Li, Yongle Chen +3
Asynchronous pipeline model parallelism with a "1F1B" (one forward, one backward) schedule generates little bubble overhead and always provides quite a high throughput. However, th…
TransferFuzz: Fuzzing with Historical Trace for Verifying Propagated Vulnerability Code
Siyuan Li, Yuekang Li, Zuxin Chen +5
Code reuse in software development frequently facilitates the spread of vulnerabilities, making the scope of affected software in CVE reports imprecise. Traditional methods primari…