- Soosahabi & Namsani (2026) — Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems — arXiv:2606.20470
- Chao et al. (2025) — Jailbreaking Black Box Large Language Models in Twenty Queries (PAIR) — arXiv:2310.08419
- Yu et al. (2024) — GPTFuzzer: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts — arXiv:2309.10253
- Chen et al. (2025) — StruQ: Defending Against Prompt Injection with Structured Queries — arXiv:2402.06363
- Anil et al. (2024) — Many-Shot Jailbreaking — arXiv:2404.02151
- Zou et al. (2023) — Universal and Transferable Adversarial Attacks on Aligned Language Models (GCG) — arXiv:2307.15043
- Liu et al. (2024) — Formalizing and Benchmarking Prompt Injection Attacks and Defenses — arXiv:2310.12815
- Xie et al. (2025) — SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal — arXiv:2406.14598
- Pasquini et al. (2025) — LLMmap: Fingerprinting for Large Language Models — arXiv:2403.15847
- Guan et al. (2024) — Deliberative Alignment: Reasoning Enables Safer Language Models — arXiv:2412.16339