arXiv AI September 11, 2026 By Jinyang Li, Mingyu Guo, Hung X. Nguyen

CS-Guard: Benchmarking LLM Guardrails for Code Generation Security

CS-Guard is a new benchmark that systematically evaluates guardrails for code generation security, covering 1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) for text-to-code generation, as well as 331 code prompts for code-to-code generation. The study empirically tests nine guardrails across seven large language models, finding that many guardrails fail to prevent malicious code generation, with attack success rates reaching about 50% for text-to-code and up to nearly 100% for code-to-code and FSA scenarios. CS-Guard introduces a modular three-layer guardrail taxonomy and releases its benchmark and data to support future research.

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.

arXiv AI

Jun 11

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

arXiv:2606. 11817v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code.

By Yitong Zhang, Shiteng Lu, Jia Li

llms benchmarks safety

arXiv AI

Jul 28

Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

arXiv:2607. 23088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored.

By Lixun Ma, Ruolong Ma, Bei Wang, Feng Wei, Zhenguang Liu, Lorenzo Cavallaro, Wentao Chen

llms benchmarks

arXiv Machine Learning

Jul 21

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

arXiv:2605. 26548v2 Announce Type: replace-cross Abstract: Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC).

By Hwiwon Lee, Jiawei Liu, Dongjun Kim, Wubing Xia, Ziqi Zhang, Chunqiu Steven Xia, Lingming Zhang

llms agents benchmarks safety

arXiv AI

Jun 19

Multi-View Decompilation for LLM-Based Malware Classification

arXiv:2606. 20436v1 Announce Type: cross Abstract: Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable.

By Bercan Turkmen, Vyas Raina

llms benchmarks

arXiv AI

Jun 17

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

arXiv:2510. 01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings.

By Shoumik Saha, Jifan Chen, Sam Mayers, Sanjay Krishna Gouda, Zijian Wang, Varun Kumar

llms agents multimodal benchmarks safety

arXiv Machine Learning

Jul 1

An Empirical Study of Security Calibration in Large Language Models for Code

arXiv:2606. 31159v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do models know when their generated code is insecure?

By Mohammed Latif Siddiq, Md. Nafiu Rahman, Joanna C. S. Santos

llms benchmarks

One email a morning, machine-written

Related stories

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

Multi-View Decompilation for LLM-Based Malware Classification

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks

An Empirical Study of Security Calibration in Large Language Models for Code