On AI Safety and Security Technical Debt in Engineering AI-Enabled Systems
Muhammad Tukur, Hayatullahi B. Adeyemo, Tao Chen, Nour Ali, Anis Zarrad, Rick Kazman, Marco Agus, Rami Bahsoon
cs.SE, cs.AI, cs.CR
Submitted: 2026-07-25
Comments: 64 pages, 7 figures, 8 tables, submitted to ACM Transactions on Software Engineering and Methodology (TOSEM)
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- An Empirical Study of Self-Admitted Technical Debt in Machine Learning Software
- Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspective
- Building an Open AIBOM Standard in the Wild
- Distribution-restrained Softmax Loss for the Model Robustness
Related papers
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces
- PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
- IntentCoding: Amplifying User Intent in Code Generation
- Incentives and Outcomes in Bug Bounties