Sharif Abuadbba

The paper evaluates multi-LLM strategies for secure code generation, finding that hybrid pipelines combining ensembling, static analysis, and patching achieve the strongest security performance, outperforming single models and purely collaborative systems.

The paper introduces MEntA, a highly query-efficient and surrogate-free membership inference attack that uses natural-language entailment to detect if a specific document was used by a RAG system, achieving high accuracy with only five queries.

The paper introduces APT-Agent, an automated LLM-driven framework that significantly improves penetration testing success rates by mitigating LLM hallucinations and maintaining long-term operational context.