Introducing SafeCoder

SafeCoder vs. Closed-source Code Assistants

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.

Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions

arXiv:2607. 08011v1 Announce Type: cross Abstract: Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code.

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs

Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign

arXiv:2502. 02068v3 Announce Type: replace-cross Abstract: This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software development.

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation

arXiv:2606. 05290v1 Announce Type: cross Abstract: Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture.

Training CodeParrot 🦜 from Scratch

Introducing CodeMender: an AI agent for code security

Using advanced AI to fix critical software vulnerabilities

StarCoder: A State-of-the-Art LLM for Code

Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks

arXiv:2606. 27147v1 Announce Type: cross Abstract: Unlike diffusion-based models that operate in continuous latent spaces, autoregressive unified multimodal models produce images by sequentially predicting discretized visual tokens.

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

arXiv:2606. 07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge.

RAS: Measuring LLM Safety Through Refusal Alignment

arXiv:2606. 25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their outputs violate a safety policy.