Similar Items: Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
- Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
- PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
- Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs
- Fine-Tuning Small Language Models for Solution-Oriented Windows Event Log Analysis
- ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
- Gaming the Metric, Not the Harm: Certifying Safety Audits against Strategic Platform Manipulation