Newest papers

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

Mirza Masfiqur Rahman, Ajwad Akil, Imtiaz Karim, Ashish Kundu, Ramana Rao Kompella, Elisa Bertino · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26001 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

बड़े भाषा मॉडल द्वारा उत्पन्न कोड अक्सर हर कार्यात्मक परीक्षण से गुजरता है जबकि असुरक्षित रहता है। ये सुरक्षा हल्काइयां आम हैं, उच्च आत्मविश्वास के साथ लिखी जाती हैं, और नमूने पर दोहराई जाती हैं, इसलिए जनरेटर की खुद की अनिश्चितता या स्थिर विश्लेषक उन्हें विश्वसनीय रूप से नहीं पकड़ते हैं। हम SPLASH को पेश करते हैं, जिसे ऑडिट दबाव नामक एक नया उपाय द्वारा निर्देशित किया जाता है। यह एक सुरक्षा समीक्षा और शैली समीक्षा के दौरान उत्पन्न कार्यक्रम के लिए शिक्षकों द्वारा मजबूर लॉग-वृत्तियों के विपरीत करता है। बयानों और कार्यक्रमों के साथ एकीकृत, और प्रतिस्पर्धी संपादनों के एक संभावनात्मक मॉडल पर आधारित, ऑडिट दबाव

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 SPLASH to choose the secure program among a model's candidate programs and locate the vulnerable statement, with no model training, CWE-specific rules, or internal access to the generating model. On 63,684 programs generated by 12 models for 899 tasks, SPLASH picks secure code in 74% of cases, places the vulnerable statement first in 58% of insecure programs, and chooses better than a frontier LLM judge.

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

Topics: Computer science, Code (set theory), Audit, Probabilistic logic, Computer security, Measure (data warehouse)

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