Similar Items: AutoSOUP: Safety-Oriented Unit Proof Generation for Component-level Memory-Safety Verification
- KVerus: Scalable and Resilient Formal Verification Proof Generation for Rust Code
- An Evaluation of Chat Safety Moderations in Roblox
- Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
- AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
- Gaming the Metric, Not the Harm: Certifying Safety Audits against Strategic Platform Manipulation
- Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis