方寸跃迁 FANGCUN LEAP

研究

顶会论文 发表

方寸跃迁团队成员在国际顶级会议上发表的 AI 安全研究成果。

2026
2026
WWW

A Game-Theoretic Approach against Dishonest LLM Consensus in Multi-Agent Systems

Yuhan Cao; Yu Wang; Sitong Liu; Miao Li; Yixin Tao; Tianxing He

A Game-Theoretic Approach against Dishonest LLM Consensus in Multi-Agent Systems
2026
ICML

AICrypto: A Comprehensive Benchmark For Evaluating Cryptography Capabilities of Large Language Models

Yu Wang; Yijian Liu; Liheng Ji; Han Luo; Wenjie Li; Xiaofei Zhou; Chiyun Feng; Puji Wang; Yuhan Cao; Geyuan Zhang; Xiaojian Li; Rongwu Xu; Yilei Chen; Tianxing He

AICrypto: A Comprehensive Benchmark For Evaluating Cryptography Capabilities of Large Language Models
2026
ACL

AwarenessBench: Assessing Cognitive Capabilities of Language Models

Xiaojian Li; Rongwu Xu; Tianyun Zhang; Yue Wang; Shuo Chen; Qiner Lyu; Briana Zhang; Peiran Yang; Kyle Xue Chen; Haoyuan Shi; Yu Wang; Wei Xu

2026
ICLR

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering

Baicheng Chen; Yu Wang; Ziheng Zhou; Xiangru Liu; Juanru Li; Yilei Chen; Tianxing He

CREBench: Evaluating Large Language Models in Cryptographic Binary Reverse Engineering
2026
EACL Findings

DebateQA: Evaluating Question Answering on Debatable Knowledge

Rongwu Xu; Xuan Qi; Zehan Qi; Wei Xu; Zhijiang Guo

DebateQA: Evaluating Question Answering on Debatable Knowledge
2026
ICML

Reverse-Engineering Model Editing on Language Models

Zhiyu Sun; Minrui Luo; Yu Wang; Zhili Chen; Tianxing He

Reverse-Engineering Model Editing on Language Models
2025
2025
IJCV

A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking

Chang Liu; Yinpeng Dong; Wenzhao Xiang; Xiao Yang; Hang Su; Jun Zhu; Yuefeng Chen; Yuan He; Hui Xue; Shibao Zheng

A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinking
2025
ICCV

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?

Shouwei Ruan; Hanqing Liu; Yao Huang; Xiaoqi Wang; Caixin Kang; Hang Su; Yinpeng Dong; Xingxing Wei

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
2025
ACL

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space

Yao Huang; Yitong Sun; Shouwei Ruan; Yichi Zhang; Yinpeng Dong; Xingxing Wei

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
2025
arXiv

Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems

Yuhan Cao; Zian Chen; Kun Quan; Ziliang Zhang; Yu Wang; Xiaoning Dong; Yeqi Feng; Guanzhong He; Jingcheng Huang; Jianhao Li; Yixuan Tan; Jiafu Tang; Yilin Tang; Junlei Wu; Qianyu Xiao; Can Zheng; Shouchen Zhou; Yuxiang Zhu; Yiming Huang; Tian Xie; Tianxing He

Can LLMs Generate Reliable Test Case Generators? A Study on Competition-Level Programming Problems
2025
NeurIPS

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios

Yao Huang; Yitong Sun; Yichi Zhang; Ruochen Zhang; Yinpeng Dong; Xingxing Wei

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
2025
TPAMI

Distributionally Location-Aware Transferable Adversarial Patches for Facial Images

Xingxing Wei; Shouwei Ruan; Yinpeng Dong; Hang Su; Xiaochun Cao

Distributionally Location-Aware Transferable Adversarial Patches for Facial Images
2025
ACL Findings

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?

Chengda Lu; Xiaoyu Fan; Yu Huang; Rongwu Xu; Jijie Li; Wei Xu

Does Chain-of-Thought Reasoning Really Reduce Harmfulness from Jailbreaking?
2025
ICCV

Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation

Shengfang Zhai; Jiajun Li; Yue Liu; Huanran Chen; Zhihua Tian; Wenjie Qu; Qingni Shen; Ruoxi Jia; Yinpeng Dong; Jiaheng Zhang

Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
2025
EMNLP

Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization

Siyuan Zhang; Yichi Zhang; Yinpeng Dong; Hang Su

Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization
2025
IJCV

Face3DAdv: Exploiting Robust Adversarial 3D Patches on Physical Face Recognition

Xiao Yang; Longlong Xu; Tianyu Pang; Yinpeng Dong; Yikai Wang; Hang Su; Jun Zhu

Face3DAdv: Exploiting Robust Adversarial 3D Patches on Physical Face Recognition
2025
ACL

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

Yu Wang; Xiaofei Zhou; Yichen Wang; Geyuan Zhang; Tianxing He

Jailbreak Large Vision-Language Models Through Multi-Modal Linkage
2025
NeurIPS

Mitigating Overthinking in Large Reasoning Models via Manifold Steering

Yao Huang; Huanran Chen; Shouwei Ruan; Yichi Zhang; Xingxing Wei; Yinpeng Dong

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
2025
ACL Findings

Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents

Rongwu Xu; Xiaojian Li; Shuo Chen; Wei Xu

Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agents
2025
TPAMI

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model

Xingxing Wei; Caixin Kang; Yinpeng Dong; Zhengyi Wang; Shouwei Ruan; Yubo Chen; Hang Su

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
2025
NeurIPS

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling

Yichuan Cao; Yibo Miao; Xiao-Shan Gao; Yinpeng Dong

Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling
2025
ACL Findings

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage

Xiaoning Dong; Wenbo Hu; Wei Xu; Tianxing He

SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
2025
ICML

STAIR: Improving Safety Alignment with Introspective Reasoning

Yichi Zhang; Siyuan Zhang; Yao Huang; Zeyu Xia; Zhengwei Fang; Xiao Yang; Ranjie Duan; Dong Yan; Yinpeng Dong; Jun Zhu

STAIR: Improving Safety Alignment with Introspective Reasoning
2024
2024
EMNLP

Course-Correction: Safety Alignment Using Synthetic Preferences

Rongwu Xu; Yishuo Cai; Zhenhong Zhou; Renjie Gu; Haiqin Weng; Yan Liu; Tianwei Zhang; Wei Xu; Han Qiu

Course-Correction: Safety Alignment Using Synthetic Preferences
2024
ECCV

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks

Caixin Kang; Yinpeng Dong; Zhengyi Wang; Shouwei Ruan; Yubo Chen; Hang Su; Xingxing Wei

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
2024
NeurIPS

Diffusion Models are Certifiably Robust Classifiers

Huanran Chen; Yinpeng Dong; Shitong Shao; Zhongkai Hao; Xiao Yang; Hang Su; Jun Zhu

Diffusion Models are Certifiably Robust Classifiers
2024
ICML

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

Shuyu Cheng; Yibo Miao; Yinpeng Dong; Xiao Yang; Xiao-Shan Gao; Jun Zhu

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
2024
ICLR

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

Lingxuan Wu; Xiao Yang; Yinpeng Dong; Liuwei Xie; Hang Su; Jun Zhu

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
2024
CVPR

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models

Yichi Zhang; Yinpeng Dong; Siyuan Zhang; Tianzan Min; Hang Su; Jun Zhu

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
2024
CVPR

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training

Qian Li; Yuxiao Hu; Yinpeng Dong; Dongxiao Zhang; Yuntian Chen

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
2024
EMNLP Findings

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States

Zhenhong Zhou; Haiyang Yu; Xinghua Zhang; Rongwu Xu; Fei Huang; Yongbin Li

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
2024
NeurIPS

Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective

Yibo Miao; Yinpeng Dong; Jinlai Zhang; Lijia Yu; Xiao Yang; Xiao-Shan Gao

2024
EMNLP

Knowledge Conflicts for LLMs: A Survey

Rongwu Xu; Zehan Qi; Zhijiang Guo; Cunxiang Wang; Hongru Wang; Yue Zhang; Wei Xu

Knowledge Conflicts for LLMs: A Survey
2024
EMNLP Findings

LONG2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall

Zehan Qi; Rongwu Xu; Zhijiang Guo; Cunxiang Wang; Hao Zhang; Wei Xu

LONG2RAG: Evaluating Long-Context & Long-Form Retrieval-Augmented Generation with Key Point Recall
2024
ICML

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning

Zhuo Huang; Chang Liu; Yinpeng Dong; Hang Su; Shibao Zheng; Tongliang Liu

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
2024
USENIX Security

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction

Tong Liu; Yingjie Zhang; Zhe Zhao; Yinpeng Dong; Guozhu Meng; Kai Chen

Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction
2024
NeurIPS

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy

Shengfang Zhai; Huanran Chen; Yinpeng Dong; Jiajun Li; Qingni Shen; Yansong Gao; Hang Su; Yang Liu

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
2024
NeurIPS

MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models

Yichi Zhang; Yao Huang; Yitong Sun; Chang Liu; Zhe Zhao; Zhengwei Fang; Yifan Wang; Huanran Chen; Xiao Yang; Xingxing Wei; Hang Su; Yinpeng Dong; Jun Zhu

MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
2024
ACM MM

Natural Language Induced Adversarial Images

Xiaopei Zhu; Peiyang Xu; Guanning Zeng; Yinpeng Dong; Xiaolin Hu

Natural Language Induced Adversarial Images
2024
ECCV

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models

Shouwei Ruan; Yinpeng Dong; Hanqing Liu; Yao Huang; Hang Su; Xingxing Wei

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models
2024
arXiv

On the Role of Attention Heads in Large Language Model Safety

Zhenhong Zhou; Haiyang Yu; Xinghua Zhang; Rongwu Xu; Fei Huang; Kun Wang; Yang Liu; Junfeng Fang; Yongbin Li

On the Role of Attention Heads in Large Language Model Safety
2024
ACL Findings

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning

Rongwu Xu; Zehan Qi; Wei Xu

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
2024
ICLR

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Huanran Chen; Yichi Zhang; Yinpeng Dong; Xiao Yang; Hang Su; Jun Zhu

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
2024
ICML

Robust Classification via a Single Diffusion Model

Huanran Chen; Yinpeng Dong; Zhengyi Wang; Xiao Yang; Chengqi Duan; Hang Su; Jun Zhu

Robust Classification via a Single Diffusion Model
2024
EMNLP Findings

Sing it, Narrate it: Quality Musical Lyrics Translation

Zhuorui Ye; Jinhan Li; Rongwu Xu

Sing it, Narrate it: Quality Musical Lyrics Translation
2024
NeurIPS

T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models

Yibo Miao; Yifan Zhu; Yinpeng Dong; Lijia Yu; Jun Zhu; Xiao-Shan Gao

T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
2024
ACL

The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation

Rongwu Xu; Brian S. Lin; Shujian Yang; Tianqi Zhang; Weiyan Shi; Tianwei Zhang; Zhixuan Fang; Wei Xu; Han Qiu

The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversation
2024
ICML

Toward Availability Attacks in 3D Point Clouds

Yifan Zhu; Yibo Miao; Yinpeng Dong; Xiao-Shan Gao

Toward Availability Attacks in 3D Point Clouds
2024
CVPR

Towards Transferable Targeted 3D Adversarial Attack in the Physical World

Yao Huang; Yinpeng Dong; Shouwei Ruan; Xiao Yang; Hang Su; Xingxing Wei

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
2024
EMNLP

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias

Rongwu Xu; Zi'an Zhou; Tianwei Zhang; Zehan Qi; Su Yao; Ke Xu; Wei Xu; Han Qiu

Walking in Others' Shoes: How Perspective-Taking Guides Large Language Models in Reducing Toxicity and Bias