Only output filtering with hardcoded rules in application code prevented prompt injection leaks in LLMs, as all model-based defenses were defeated by an adaptive attacker.
Top 10 for Large Language Model Applications v2025.https://genai.owasp.org/ llmrisk/llm01-prompt-injection/
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Evaluation of Prompt Injection Defenses in Large Language Models
Only output filtering with hardcoded rules in application code prevented prompt injection leaks in LLMs, as all model-based defenses were defeated by an adaptive attacker.