AI Paper Atlas

Research map / Large language models / Agents, code and math

Scam2Prompt: A Scalable Framework for Auditing Malicious Scam Endpoints in Production LLMs

Zhiyang Chen, Tara Saba, Xun Deng, Xujie Si, Fan Long

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use gpt-4o-mini instead of llama-4-scout as the Prompt LLM (gpt-4o codegen)Scam2Prompt · Scam2Prompt auditmalicious program rate (%): 3.54% -> 5.94%Hurt
use llama-4-scout instead of gpt-4o as Codegen LLM (gpt-4o-mini prompts)Scam2Prompt · Scam2Prompt auditmalicious program rate (%): 5.94% -> 4.64%Improved
add aggressive content filtering (gemini-2.5-pro vs gpt-5)gemini-2.5-pro · Innoc2Scam-benchmalicious rate (%): 22.0% -> 12.9%Improved
condition on completed outputs only (remove refusals)gemini-2.5-pro · Innoc2Scam-benchmalicious rate (%): 12.9% -> 22.28%Hurt
add NeMo Guardrails with Llama Nemotron Safety Guard V2LLM code generation · Innoc2Scam-benchmalicious detection rate: 0 to 0.7%No clear effect
add OpenAI Moderation APILLM code generation · Innoc2Scam-benchflagged malicious outputs: 0 of 3,452No clear effect
add Llama Guard 3LLM code generation · Innoc2Scam-benchflagged malicious outputs: 291/3,452 (8.43%)No clear effect
add RAG web-search agent with URL safety instructionGPT-4o · Innoc2Scam-benchmalicious URL generation rate (%): 50.04% -> 29.41%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy