arXiv AI
CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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.
arXiv AI
Jul 3
Safety Targeted Embedding Exploit via Refinement
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
Hugging Face Trending Papers
Jul 2
Safety Targeted Embedding Exploit via Refinement
Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching. We show that this creates an epistemic gap in which models confidently generate harmful responses for inputs that fall outside the distribution of their safety training.
arXiv Machine Learning
Jun 30
Sparse Autoencoders are Capable LLM Jailbreak Mitigators
arXiv:2602. 12418v2 Announce Type: replace-cross Abstract: Jailbreak attacks remain a persistent threat to large language model safety.
arXiv Computation and Language
Sep 23
Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs
arXiv:2609.26185v1 Announce Type: cross Abstract: Large Language Models (LLMs) demonstrate impressive capabilities across many applications but remain vulnerable to jailbreak attacks, which elicit ha...
arXiv AI
Jul 23
JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models
arXiv:2607. 19424v1 Announce Type: cross Abstract: The assessment of jailbreak attacks against large language models currently suffers from inconsistent evaluation criteria and methods, leading to unreliable estimates of attack success rates.