Detecting Prompt Injection Attacks Against Application Using Classifiers
On the map: LLM safety and security → Prompt injection and agent security
Abstract (arXiv)
Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM, feed forward neural networks, Random Forest, and Naive Bayes, to detect malicious prompts in LLM integrated web applications. The proposed approach improves prompt injection detection and mitigation, helping protect targeted applications and systems.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. Builds on 9 of its 14 references that are in the map. First posted on arXiv 14 Dec 2025.
Builds on
9 of 14 references.
Closest ancestors · 4
Same direction, newest first
- 2023From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?3 Aug
- 2023From ChatGPT to ThreatGPT: Impact of Generative AI in Cybersecurity and Privacy3 Jul
- 2023Multi-step Jailbreaking Privacy Attacks on ChatGPT11 Apr
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection23 Feb
Other references · 5
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,538
- 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
- 2016SelQA: A New Benchmark for Selection-based Question Answeringcited by 6
Built on by
Citing papers per year: 2026: 1.
1 paper.