Prompt Injection Defense

Latest papers 102

17 papers in the last four weeks, up 113% on the four weeks before. 0.1% of all new papers.

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs
Mar 29, 2026Alexandre Cristovão MaioranoPrompt Injection Defense LLM Guardrails
The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense
Mar 24, 2026Qianlong Lan, Anuj KaulAI Agent Security Prompt Injection Defense
eBay Inc
The Autonomy Tax: Defense Training Breaks LLM Agents
Mar 19, 2026Shawn Li, Yue ZhaoAI Agent Security LLM Agents
University of Southern California
PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses
Mar 13, 2026Chenlong Yin, Runpeng Geng, Yanting Wang +1Prompt Injection Attacks on LLMs LLM Red Teaming
The Pennsylvania State University
Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
Mar 13, 2026Darren Cheng, Wen-Kwang TsaoPrompt Injection Defense AI Agent Security
TrendAI Lab
The Mirror Design Pattern: Strict Data Geometry over Model Scale for Prompt Injection Detection
Mar 12, 2026J Alex CorllPrompt Injection Defense Prompt Injection Detection
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Feb 26, 2026Tian Zhang, Yiwei Xu, Juan Wang +8Prompt Injection Defense Prompt Injection Attacks on AI Agents
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan 430072, China · Department of Computer Science and Engineering, University at Buffalo, SUNY · Department of Computer Science, College of Information Science and Technology, Jinan University, Guangzhou 510632, China +1
Analysis of LLMs Against Prompt Injection and Jailbreak Attacks
Feb 24, 2026Piyush Jaiswal, Aaditya Pratap, Shreyansh Saraswati +2Prompt Injection Attacks on LLMs Language Model Safety Evaluation
NIT Trichy, Tiruchirappalli, India · NCE Chandi, Nalanda, India · Bishop Cotton Boys’ School, Bengaluru, India +2
ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction
Feb 24, 2026Che Wang, Fuyao Zhang, Jiaming Zhang +6Prompt Injection Defense AI Agent Security
School of Computer Science, Peking University, China · College of Computing and Data Science, Nanyang Technological University, Singapore · Ant Group +1
Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification
Nov 23, 2025Yanxi Li, Ruocheng ShanPrompt Injection Defense Prompt Injection Attacks on LLMs
Department of Computer Science, George Washington University, Washington, DC, USA
Meta-SecAlign: Training LLMs against Prompt Injection for Robust Agents
Jul 3, 2025Sizhe Chen, Arman Zharmagambetov, David Wagner +1LLM Agent Security AI Agent Security Benchmarks
FAIR at Meta · UC Berkeley
Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
May 21, 2025Xiaoxue Yang, Bozhidar Stevanoski, Matthieu Meeus +1Prompt Injection Defense Prompt Injection Attacks on LLMs
Imperial College London

Mar 29, 2026J/K move · Enter open · S save

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs

Alexandre Cristovão Maiorano

Prompt Injection Defense LLM Guardrails Language Model Safety Evaluation Prompt Injection Attacks on LLMs Generative AI in Education

Open paper AskPDF arXiv

Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency. We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural validation, contextual sandboxing, and session-level behavioral checks. On a controlled holdout benchmark, the pipeline reaches low bypass and false positive rates with optimized average latency - an operating point that prioritizes pedagogical usability (zero false positives) while maintaining measurable attack resistance. We provide a reproducible benchmark protocol for head-to-head comparison under identical conditions, including stratified bootstrap confidence intervals, paired McNemar significance tests, multi-seed sensitivity sweeps, and direct evaluation of Prompt Guard and NeMo Guardrails on the same split with unified instrumentation. Results expose operational trade-offs: NeMo reaches 0 percent bypass at 16.22 percent FPR and roughly 1.5s latency, while Prompt Guard yields 38.48 percent bypass with 3.60 percent FPR. The framework supports evidence-based guardrail selection for AI tutoring systems under different institutional risk and usability requirements.