Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
JATMO: Prompt injection defense by task-specific finetuning
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
The method prompts LLMs to output both answers and references to the executed instructions, then filters out any answers not linked to the original input instructions, reducing attack success rates to zero in tested scenarios while preserving utility.
Systematic testing of ten LLM agents across 20 tool scenarios and 14 attacks finds universal vulnerability to prompt injection enabling data exfiltration, with tooling amplifying leakage.
SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
A survey reviewing the integration of generative models with connected and automated vehicles to enhance predictive modeling, simulation accuracy, and decision-making.
citing papers explorer
-
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
-
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
The method prompts LLMs to output both answers and references to the executed instructions, then filters out any answers not linked to the original input instructions, reducing attack success rates to zero in tested scenarios while preserving utility.
-
Whispers in the Machine: Confidentiality in Agentic Systems
Systematic testing of ten LLM agents across 20 tool scenarios and 14 attacks finds universal vulnerability to prompt injection enabling data exfiltration, with tooling amplifying leakage.
-
SafeAgent: A Runtime Protection Architecture for Agentic Systems
SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
-
Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI
A survey reviewing the integration of generative models with connected and automated vehicles to enhance predictive modeling, simulation accuracy, and decision-making.