Mimic

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 20

All topics

CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion
Sep 30, 2026Zhen Liang, Hai Huang, Wentao ChenJailbreak Attacks Vulnerable Code
School of Computer Science and Technology, Zhejiang Sci-Tech University · Zhejiang Key Laboratory of Digital Fashion and Data Governance, Zhejiang Sci-Tech University · China Academy of Information and Communications Technology
RootQuantV2: Adapting a Vision Foundation Model for Root-Trait Regression from Minirhizotron Imagery
Sep 22, 2026Kinjalk Parth, Sebastian Varela, Andrew D. B. LeakeyTomato Diseases Vision Foundation Models
Department of Plant Biology, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA · Center for Advanced Bioenergy and Bioproducts Innovation, Urbana, IL 61801, USA
MimicAgent: Quadruped Skills via Prompt-to-Trajectory Generation
Sep 21, 2026Lucky Kant Nayak, Narayanan Palghat Parameswaran, Neehar Peri +1Mimic Skills
Carnegie Mellon University
SignMimic: Robust High-Quality Sign Language Motion Generation via Human-Shape-Oblivious Pose Transfer Guidance
Sep 12, 2026Zhewen He, Junyi Yu, Haomian Huang +2Sign Language Translation Mimic
New York University Abu Dhabi · ChatSign Technology
InstantMimic: A High Performance System for Learning Physics-based Skills in Seconds
Sep 9, 2026Ikjun Choi, Geonho Leem, Jungdam WonMimic Skills
Seoul National University, Seoul, South Korea
StableMimic: Smooth Human-Like Recovery for Humanoid Motion Tracking - Learning Beyond the Tracking Distribution for Structured Post-Fall Behavior
Aug 3, 2026Weihao Wu, Ming Huang, Ruofei Liu +3Robust Fall Detection Mimic
Southern University of Science and Technology (SUSTech), Shenzhen, China.
FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry
Jul 20, 2026Dingyun Zhang, Lixue Gong, Wei LiuVideo Editing Long Video Generation
1ByteDance
Comparative Analysis of GAT and BERT for Human-Like Playtesting
Jul 13, 2026Kleio Fragkedaki, Theodoros Panagiotakopoulos, Matteo Biasielli +1Puzzle Comparison
AI Center of Excellence King Stockholm, Sweden
ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments
Jul 2, 2026Lu Pan, Hongwei ZhaoMotion Imitation Imitation Learning
College of Computer Science and Technology, Jilin University, China · Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, China
PressMimic: Pressure-Guided Motion Capture and Control for Humanoid Robot Imitation
Jun 25, 2026Yi Lu, Shenghao Ren, Tianyu Xiong +6Motion Imitation Motion Capture
School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China. · BNRist, Tsinghua University, Beijing 100084, China. · Key Laboratory of Optoelectronic Devices and Systems with Extreme Performances of MOE, Nanjing University, Nanjing 210023, China.
ActiveMimic: Egocentric Video Pretraining with Active Perception
Jun 4, 2026Xingyao Lin, Guojin Zhong, Tianyi Lu +4Egocentric Video Mimic
Fudan University · Shanghai Innovation Institute · Current Robotics +1
M3imic: Learning a Versatile Whole-Body Controller for Multimodal Motion Mimicking
Jun 3, 2026Zuxing Lu, Ziang Zheng, Yao Lyu +7Whole-Body Control Mimic
School of Automation, Southeast University, Nanjing 210096, China · School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China · Department of Robotics, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi 7909, UAE
Constrained Whole-Body Tracking for Humanoid Robots
May 29, 2026Daniel Morton, Pranit Mohnot, Marco PavoneRobot Systems Mimic
Stanford University · NVIDIA Research
Steer Like the LLM: Activation Steering that Mimics Prompting
May 5, 2026Geert Heyman, Frederik VandeputteLinear Activation Steering Instruction-Tuned Models
Nokia Bell Labs, Belgium.
Language models fail at extended rule following
May 3, 2026Tianxiang Dai, Jonathan FanLarge Language Models Fail Mimic
Department of Electrical Engineering, Stanford University, Stanford, CA 94305.
MIMIC: A Generative Multimodal Foundation Model for Biomolecules
Apr 27, 2026Siavash Golkar, Jake Kovalic, Irina Espejo Morales +28Molecular Design Multimodal Foundation Model
Polymathic AI · Center for Data Science, New York University · Department of Applied Physics, Yale University +17
Long-tail Internet photo reconstruction
Apr 24, 2026Yuan Li, Yuanbo Xiangli, Hadar Averbuch-Elor +2Large-Scale 3D Editing Dataset Long-Tailed Distribution
Cornell University · 2Kempner Institute, Harvard University
MiMIC: Mitigating Visual Modality Collapse in Universal Multimodal Retrieval While Avoiding Semantic Misalignment
Apr 23, 2026Juan Li, Chuanghao Ding, Xujie Zhang +1Multimodal Retrieval Mimic
State Key Laboratory for Novel Software Technology, Nanjing University
CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance
Apr 1, 2026Haochen Liu, Weien Li, Rui Song +6Evidence Conflict Mimic
University of Cambridge · McGill University · MBZUAI - Mohamed bin Zayed University of Artificial Intelligence +2
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
Date pendingDayi Dong, Maulik Bhatt, Seoyeon Choi +1Multi-Agent Coordination Diffusion Policies
Department of Mechanical Engineering, University of California Berkeley, Berkeley, CA 94709, USA

Sep 30, 2026, cs.CRJ/K move · Enter open · S save

CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion

Zhen Liang, Hai Huang, Wentao Chen

School of Computer Science and Technology, Zhejiang Sci-Tech University · Zhejiang Key Laboratory of Digital Fashion and Data Governance, Zhejiang Sci-Tech University · China Academy of Information and Communications Technology

Jailbreak Attacks Vulnerable Code Code Completion Mimic

Open paper AskPDF arXiv

Large language models have achieved remarkable capabilities across diverse domains, yet their safety alignment remains vulnerable to jailbreak attacks. In this work, we identify a previously underexplored failure mode - safety generalization lag - where alignment trained predominantly on natural language fails to transfer to the code domain. We show that this lag induces a code-completion blind spot, allowing malicious intent embedded within syntactically valid code to evade safety mechanisms. To exploit this vulnerability, we propose CodeMimicry, a fully automated black-box jailbreak framework that generates structured, object-oriented code prompts to induce harmful outputs via code completion. Experiments on 8 state-of-the-art commercial LLMs demonstrate that CodeMimicry achieves a 96.25% attack success rate with 1.51 queries on average, significantly outperforming both template-based and optimization-based baselines. Beyond empirical performance, we provide a mechanistic analysis of code-based jailbreaks through latent space representations, including projection onto refusal-related directions and activation steering. This analysis offers an explanation of how CodeMimicry bypasses safety mechanisms in code-related domains. Our findings reveal a weakness in current safety alignment and highlight the need for robust alignments in structured domains such as code.

Momentum

Related topics

Latest papers 20