Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

Documenti analoghi

• CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning
  di: ElZemity, Adel, et al.
  Pubblicazione: (2025)
• Privacy Threats and Countermeasures in Federated Learning for Internet of Things: A Systematic Review
  di: ElZemity, Adel, et al.
  Pubblicazione: (2024)
• APIOT: Autonomous Vulnerability Management Across Bare-Metal Industrial OT Networks
  di: ElZemity, Adel, et al.
  Pubblicazione: (2026)
• Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection
  di: ElZemity, Adel, et al.
  Pubblicazione: (2026)
• Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
  di: Mao, Qinghua, et al.
  Pubblicazione: (2026)