Presents a byte-native LLM with bespoke tokenizer achieving 69-98% accuracy on malware family and architecture classification from raw bytes.
Co-redteam: Orchestrated security discovery and exploitation with llm agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 5years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Revelio combines LLMs, static analysis, and sanitizer-verified PoVs to scalably discover memory safety vulnerabilities in repository-scale code, finding 19 new bugs in long-fuzzed projects at low cost.
CAESAR decomposes LLM-based intrusion workflows into five roles with bounded coordination protocols, yielding higher success rates and lower variance than single-agent baselines on 25 CTF tasks.
The paper proposes the Cybersecurity AI Scientist as a modular multi-agent architecture for automating cybersecurity research, distinguished by its focus on non-stationary threats and anchored in a four-zeros risk-trust-incident-energy frame.
CSI meta-scaffold unifies five LLM agent harnesses; a blackboard multi-agent system solves 19/33 cybench challenges (57.6%) versus 15/33 for the best single scaffold.
citing papers explorer
-
Large Byte Model: Teaching Language Models About Compiled Code
Presents a byte-native LLM with bespoke tokenizer achieving 69-98% accuracy on malware family and architecture classification from raw bytes.
-
Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases
Revelio combines LLMs, static analysis, and sanitizer-verified PoVs to scalably discover memory safety vulnerabilities in repository-scale code, finding 19 new bugs in long-fuzzed projects at low cost.
-
When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions
CAESAR decomposes LLM-based intrusion workflows into five roles with bounded coordination protocols, yielding higher success rates and lower variance than single-agent baselines on 25 CTF tasks.
-
Hephaestus: Toward a Cybersecurity AI Scientist
The paper proposes the Cybersecurity AI Scientist as a modular multi-agent architecture for automating cybersecurity research, distinguished by its focus on non-stationary threats and anchored in a four-zeros risk-trust-incident-energy frame.
-
Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?
CSI meta-scaffold unifies five LLM agent harnesses; a blackboard multi-agent system solves 19/33 cybench challenges (57.6%) versus 15/33 for the best single scaffold.