Similar Items: AdaBFL: Multi-Layer Defensive Adaptive Aggregation for Bzantine-Robust Federated Learning
- Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Study
- On the (In-)Security of the Shuffling Defense in the Transformer Secure Inference
- Cryptographic Registry Provenance: Structural Defense Against Dependency Confusion in AI Package Ecosystems
- TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
- Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense
- Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery