arXiv (All)
open access
Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks
Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in 0.3-3.4% of traces, implicating only a handful of models. We present a controlled prompt-ablation study across 22 fron
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- FATS: A Prompt Injection Attack Utilizing Feign Security Agents with Deceptive Few-shots Learning#972881
- Harness-agnostic detection and immunization of reward hacking in self-evolving language models#927932
- SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models#1344697
- SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models#1318896
- Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States#1117751
Record · ID 1386324
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive