← Back to all news
arXiv AI By Wenbin Chen, Jiexin Wang, Guanting Wu, Jiaxi Liang, Yi Cai

SpecCloak: Probing Harmful Code Generation through Engineering Specifications

Read the original on arXiv AI →

SpecCloak investigates how presenting coding tasks as engineering specifications—via the PseudoSpec template—affects large language models’ refusal to generate harmful code. Experiments on five open-weight models show that specification prompting significantly lowers refusal rates even when risk keywords remain, shifting internal representations toward code-output contexts. Building on this, SpecCloak combines PseudoSpec with discriminator-guided optimization to achieve a 28.91% attack success rate, while SpecReveal offers a defense that detects such attacks with 96.88% accuracy without fine‑tuning the target model.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computation and Language
Sep 15

Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking

arXiv:2407.02395v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for program synthesis, yet they often generate code that is functionally plausible but ins...

By Jiexin Wang, Liuwen Cao, Xitong Luo, Yang Cao, Zhenghao Li, Yunyi Xiao, Mengchen Zhao, Adam Jatowt, Yi Cai
llmsagentsbenchmarks
More like this →
arXiv AI
Sep 25

Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning

The paper introduces CodeScan, a black-box, vulnerability-oriented scanning framework designed to detect data poisoning and backdoor attacks in code generation large language models (LLMs). CodeScan operates by analyzing structural similarities across multiple code generations, normalizing them with abstract syntax tree (AST) techniques, and then applying LLM-based vulnerability analysis to identify recurring insecure patterns. Evaluations on 117 models across three architectures and multiple sizes show over 97% detection accuracy with fewer false positives compared to prior methods.

By Shenao Yan, Shan Jin, Shimaa Ahmed, Sunpreet Singh Arora, Yiwei Cai, Yizhen Wang, Yuan Hong
llms
More like this →
arXiv AI
Jul 8

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

arXiv:2607. 05842v1 Announce Type: cross Abstract: Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair can closely resemble terminology associated with misuse.

By Mingchen Li, Meikang Qiu, Zifan Peng, Heng Fan, Song Fu, Junhua Ding, Yunhe Feng
llmssafety
More like this →