Seven cross-domain prompt-injection detectors are introduced; three are shipped and d028 raises F1 on paraphrased attacks from 0.033 to 0.378, while adaptive-attack support remains unevaluated.
Hacking back the ai-hacker: Prompt injection as a defense against llm-driven cyberattacks
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Injecting one poisoned playbook into security knowledge sources causes systematic behavior changes in RAG AI agents across multiple LLMs and tasks, explained by a Verification Boundary classification.
Detect-and-misdirect defenses bound asymptotic attacker success rates in model-guided jailbreaks on agentic AI, unlike detect-and-block which permit near-certain success with sufficient queries.
Agentic LLM systems for reverse engineering fail on obfuscation, timing, and unique architectures due to token limits and missing guardrails, with challenges and directions proposed.
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
citing papers explorer
-
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
Seven cross-domain prompt-injection detectors are introduced; three are shipped and d028 raises F1 on paraphrased attacks from 0.033 to 0.378, while adaptive-attack support remains unevaluated.
-
Poisoned Playbooks: Demystifying Knowledge Poisoning Effects on AI Security Agents
Injecting one poisoned playbook into security knowledge sources causes systematic behavior changes in RAG AI agents across multiple LLMs and tasks, explained by a Verification Boundary classification.
-
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
Detect-and-misdirect defenses bound asymptotic attacker success rates in model-guided jailbreaks on agentic AI, unlike detect-and-block which permit near-certain success with sufficient queries.
-
Challenges and Future Directions in Agentic Reverse Engineering Systems
Agentic LLM systems for reverse engineering fail on obfuscation, timing, and unique architectures due to token limits and missing guardrails, with challenges and directions proposed.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.