Newest papers

SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated Code

Mirza Masfiqur Rahman, MD Ajwad Akil, Imtiaz Karim, Ashish Kundu, Ramana Kompella, Elisa Bertino · 2026 · arXiv

DOI: 10.48550/arXiv.2610.26001 · open-access PDF

Korean

대형 언어 모델에 의해 생성 된 코드는 종종 모든 기능 테스트를 통과하면서 불안정합니다.이 보안 환각은 일반적이며, 높은 신뢰성으로 작성되며 샘플을 통해 반복되므로 생성기 자체의 불확실성이나 정적 분석기가 신뢰할 수 없기 때문에 SPLASH를 도입합니다.우리는 감사 압력이라고 불리는 새로운 측정에 의해 지시됩니다.그것은 보안 검토 및 스타일 검토를 통해 생성 된 프로그램에 대한 교사에 의한 강제 로그 확률을 대조합니다.설명 및 프로그램에 합병하고 경쟁 편집의 확률 모델에 기반을 둔 감사 압력은 S를 허용합니다.

Machine translation (Meta M2M100); the English original follows.

Abstract

Code generated by large language models often passes every functional test while remaining insecure. These security hallucinations are common, written with high confidence, and repeated across samples, so neither the generator's own uncertainty nor static analyzers reliably catch them. We introduce SPLASH, which is guided by a new measure called audit pressure. It contrasts teacher-forced log-probabilities for the generated program under a security review and a style review. Aggregated to statements and programs, and grounded in a probabilistic model of competing edits, audit pressure allows S

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26001, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange