---
title: "Who cites Xiaogeng Liu — 423 papers of our library"
description: "423 papers of the Elamur Research library cite the works of Xiaogeng Liu, found in their bibliographies · page 1 of 2 · 1–100; the most cited first."
canonical: "https://research.elamur.ai/free/en/authors/xiaogeng-liu/cited-by/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiaogeng-liu/cited-by/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Xiaogeng Liu](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/) / cited by

# Who cites Xiaogeng Liu

446 citations of their works from 423 papers of our library (of the 149,439 whose bibliographies we read) · 113 with a page here, the most cited first · page 1 of 2 · 1–100 · [← Xiaogeng Liu](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/)

**1** [2](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/cited-by/page/2/) [next →](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/cited-by/page/2/)

1. [**A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly arXiv:2312.02003**Yifan Yao, Jinhao Duan, Kaidi Xu, et al.*2023 · 1,186 citations*](https://md.research.elamur.ai/free/en/papers/yao-2023-survey-large-language-model-llm/)
2. [**Qwen2.5-VL Technical Report arXiv:2502.13923**Shuai Bai, Keqin Chen, Xuejing Liu, et al.*2025 · 1,031 citations*](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
3. [**LLaVA-OneVision: Easy Visual Task Transfer arXiv:2408.03326**Bo Li, Yuanhan Zhang, Dong Guo, et al.*2024 · 477 citations*](https://md.research.elamur.ai/free/en/papers/li-2024-llava-onevision-easy-visual-task/)
4. **[Security and Privacy Challenges of Large Language Models: A Survey](https://md.research.elamur.ai/free/en/papers/das-2024-security-privacy-challenges-large-language/) [ACM Computing Surveys](https://md.research.elamur.ai/free/en/venues/acm-computing-surveys/)**Badhan Chandra Das, M. Hadi Amini, Yanzhao Wu*2024 · 424 citations*
5. [**Qwen3-VL Technical Report arXiv:2511.21631**Shuai Bai, Yuxuan Cai, Ruizhe Chen, et al.*2025 · 370 citations*](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen3-vl-technical-report/)
6. [**HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal arXiv:2402.04249**Mantas Mazeika, Long Phan, Xuwang Yin, et al.*2024 · 330 citations*](https://md.research.elamur.ai/free/en/papers/mazeika-2024-harmbench-standardized-evaluation-framework-automated/)
7. [**Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling arXiv:2412.05271**Zhe Chen, Weiyun Wang, Yue Cao, et al.*2024 · 287 citations*](https://md.research.elamur.ai/free/en/papers/chen-2024-expanding-performance-boundaries-open/)
8. **[JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models](https://md.research.elamur.ai/free/en/papers/chao-2024-jailbreakbench-open-robustness-benchmark-jailbreaking/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Patrick Chao, Edoardo Debenedetti, Alexander Robey, et al.*2024 · 277 citations*
9. **[Tree of Attacks: Jailbreaking Black-Box LLMs Automatically](https://md.research.elamur.ai/free/en/papers/mehrotra-2023-tree-attacks-jailbreaking-black-box/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, et al.*2023 · 251 citations*
10. [**TrustLLM: Trustworthiness in Large Language Models arXiv:2401.05561**Yue Huang, Lichao Sun, Haoran Wang, et al.*2024 · 237 citations*](https://md.research.elamur.ai/free/en/papers/huang-2024-trustllm-trustworthiness-large-language-models/)
11. [**Qwen2.5-Omni Technical Report arXiv:2503.20215**Jin Xu, Zhifang Guo, Jinzheng He, et al.*2025 · 227 citations*](https://md.research.elamur.ai/free/en/papers/xu-2025-qwen2-5-omni-technical/)
12. [**InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models arXiv:2504.10479**Jinguo Zhu, Weiyun Wang, Zhe Chen, et al.*2025 · 216 citations*](https://md.research.elamur.ai/free/en/papers/zhu-2025-internvl3-exploring-advanced-training/)
13. **[How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs](https://md.research.elamur.ai/free/en/papers/zeng-2024-how-johnny-can-persuade-llms/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yi Zeng, Hongpeng Lin, Jingwen Zhang, et al.*2024 · 203 citations*
14. [**Refusal in Language Models Is Mediated by a Single Direction arXiv:2406.11717**Andy Arditi, Oscar Obeso, Aaquib Syed, et al.*2024 · 196 citations*](https://md.research.elamur.ai/free/en/papers/arditi-2024-refusal-language-models-mediated-single/)
15. [**InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency arXiv:2508.18265**Weiyun Wang, Zhangwei Gao, Lixin Gu, et al.*2025 · 179 citations*](https://md.research.elamur.ai/free/en/papers/wang-2025-internvl3-5-advancing-open/)
16. [**SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks arXiv:2310.03684**Alexander Robey, Eric Wong, Hamed Hassani, et al.*2023 · 164 citations*](https://md.research.elamur.ai/free/en/papers/robey-2023-smoothllm-defending-large-language-models/)
17. [**DeepInception: Hypnotize Large Language Model to Be Jailbreaker arXiv:2311.03191**Xuan Li, Zhanke Zhou, Jianing Zhu, et al.*2023 · 141 citations*](https://md.research.elamur.ai/free/en/papers/li-2023-deepinception-hypnotize-large-language-model/)
18. [**Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations arXiv:2310.06387**Zeming Wei, Yifei Wang, Ang Li, et al.*2023 · 130 citations*](https://md.research.elamur.ai/free/en/papers/wei-2023-jailbreak-guard-aligned-language-models/)
19. **[SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding](https://md.research.elamur.ai/free/en/papers/xu-2024-safedecoding-defending-against-jailbreak-attacks/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zhangchen Xu, Fengqing Jiang, Luyao Niu, et al.*2024 · 127 citations*
20. **[SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models](https://md.research.elamur.ai/free/en/papers/li-2024-salad-bench-hierarchical-comprehensive-safety/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Lijun Li, Bowen Dong, Ruohui Wang, et al.*2024 · 119 citations*
21. [**Certifying LLM Safety against Adversarial Prompting arXiv:2309.02705**Aounon Kumar, Chirag Agarwal, Suraj Srinivas, et al.*2023 · 113 citations*](https://md.research.elamur.ai/free/en/papers/kumar-2023-certifying-llm-safety-against-adversarial/)
22. **[Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM](https://md.research.elamur.ai/free/en/papers/cao-2024-defending-against-alignment-breaking-attacks/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Bochuan Cao, Yuanpu Cao, Lu Lin, et al.*2024 · 109 citations*
23. **[WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models](https://md.research.elamur.ai/free/en/papers/jiang-2024-wildteaming-scale-wild-jailbreaks-adversarially/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Liwei Jiang, Kavel Rao, Seungju Han, et al.*2024 · 92 citations*
24. [**GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning arXiv:2507.01006**GLM-V Team, Wenyi Hong, Wenmeng Yu, et al.*2025 · 89 citations*](https://md.research.elamur.ai/free/en/papers/team-2025-v-glm-4-5v-glm/)
25. **[Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://md.research.elamur.ai/free/en/papers/raina-2024-is-llm-as-judge-robust/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Vyas Raina, Adian Liusie, Mark Gales*2024 · 86 citations*
26. **[PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://md.research.elamur.ai/free/en/papers/ji-2025-pku-saferlhf-multi-level-safety/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jiaming Ji, Donghai Hong, Borong Zhang, et al.*2025 · 83 citations*
27. [**ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs arXiv:2402.11753**Fengqing Jiang, Zhangchen Xu, Luyao Niu, et al.*2024 · 83 citations*](https://md.research.elamur.ai/free/en/papers/jiang-2024-artprompt-ascii-art-based-jailbreak/)
28. **[The Art of Saying No: Contextual Noncompliance in Language Models](https://md.research.elamur.ai/free/en/papers/brahman-2024-art-saying-no-contextual-noncompliance/) [Conference on Neural Information Processing Systems (NeurIPS)](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/)**Faeze Brahman, Sachin Kumar, Vidhisha Balachandran, et al.*2024 · 56 citations*
29. **[mDPO: Conditional Preference Optimization for Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2024-mdpo-conditional-preference-optimization-multimodal/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Fei Wang, Wenxuan Zhou, James Y. Huang, et al.*2024 · 50 citations*
30. **[MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale](https://md.research.elamur.ai/free/en/papers/guo-2025-mammoth-vl-eliciting-multimodal-reasoning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jiawei Guo, Tianyu Zheng, Yizhi Li, et al.*2025 · 40 citations*
31. [**NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model arXiv:2508.14444**NVIDIA: Aarti Basant, Abhijit Khairnar, Abhijit Paithankar, et al.*2025 · 39 citations*](https://md.research.elamur.ai/free/en/papers/basant-2025-nvidia-nemotron-nano-2-accurate/)
32. **[Attacking Vision-Language Computer Agents via Pop-ups](https://md.research.elamur.ai/free/en/papers/zhang-2025-attacking-vision-language-computer-agents/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yanzhe Zhang, Tao Yu, Diyi Yang*2025 · 32 citations*
33. **[VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://md.research.elamur.ai/free/en/papers/hu-2025-vlsbench-unveiling-visual-leakage-multimodal/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xuhao Hu, Dongrui Liu, Hao Li, et al.*2025 · 32 citations*
34. **[Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification](https://md.research.elamur.ai/free/en/papers/zhang-2025-breaking-agents-compromising-autonomous-llm/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Boyang Zhang, Yicong Tan, Yun Shen, et al.*2025 · 29 citations*
35. [**Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming arXiv:2501.18837**Mrinank Sharma, Meg Tong, Jesse Mu, et al.*2025 · 29 citations*](https://md.research.elamur.ai/free/en/papers/sharma-2025-constitutional-classifiers-defending-against-universal/)
36. [**Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning arXiv:2512.20848**NVIDIA: Aaron Blakeman, Aaron Grattafiori, Aarti Basant, et al.*2025 · 27 citations*](https://md.research.elamur.ai/free/en/papers/blakeman-2025-nemotron-3-nano-open-efficient/)
37. **[Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding](https://md.research.elamur.ai/free/en/papers/yoo-2025-code-switching-red-teaming-llm/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Haneul Yoo, Yongjin Yang, Hwaran Lee*2025 · 26 citations*
38. **[CAMEL-Bench: A Comprehensive Arabic LMM Benchmark](https://md.research.elamur.ai/free/en/papers/ghaboura-2025-camel-bench-comprehensive-arabic-lmm/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Sara Ghaboura, Ahmed Heakl, Omkar Thawakar, et al.*2025 · 22 citations*
39. **[Intention Analysis Makes LLMs A Good Jailbreak Defender](https://md.research.elamur.ai/free/en/papers/zhang-2025-intention-analysis-makes-llms-good/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Yuqi Zhang, Liang Ding, Lefei Zhang, et al.*2025 · 21 citations*
40. **[Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking](https://md.research.elamur.ai/free/en/papers/zhu-2025-reasoning-defend-safety-aware-reasoning/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Junda Zhu, Lingyong Yan, Shuaiqiang Wang, et al.*2025 · 21 citations*
41. **[AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection](https://md.research.elamur.ai/free/en/papers/luo-2025-agrail-lifelong-agent-guardrail-effective/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Weidi Luo, Shenghong Dai, Xiaogeng Liu, et al.*2025 · 20 citations*
42. **[Jailbreak Large Vision-Language Models Through Multi-Modal Linkage](https://md.research.elamur.ai/free/en/papers/wang-2025-jailbreak-large-vision-language-models/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yu Wang, Xiaofei Zhou, Yichen Wang, et al.*2025 · 20 citations*
43. **[Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models](https://md.research.elamur.ai/free/en/papers/gao-2025-shaping-safety-boundaries-understanding-defending/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Lang Gao, Jiahui Geng, Xiangliang Zhang, et al.*2025 · 19 citations*
44. **[LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://md.research.elamur.ai/free/en/papers/ren-2025-llms-know-their-vulnerabilities-uncover/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Qibing Ren, Hao Li, Dongrui Liu, et al.*2025 · 18 citations*
45. **[Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective](https://md.research.elamur.ai/free/en/papers/li-2025-revisiting-jailbreaking-large-language-models/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Tianlong Li, Zhenghua Wang, Wenhao Liu, et al.*2025 · 17 citations*
46. [**Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation arXiv:2603.19220**Zhuolin Yang, Zihan Liu, Yang Chen, et al.*2026 · 16 citations*](https://md.research.elamur.ai/free/en/papers/yang-2026-nemotron-cascade-2-post-training/)
47. **[HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States](https://md.research.elamur.ai/free/en/papers/jiang-2025-hiddendetect-detecting-jailbreak-attacks-against/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Yilei Jiang, Xinyan Gao, Tianshuo Peng, et al.*2025 · 15 citations*
48. [**When "Competency" in Reasoning Opens the Door to Vulnerability: Jailbreaking LLMs via Novel Complex Ciphers arXiv:2402.10601**Divij Handa, Zehua Zhang, Amir Saeidi, et al.*2024 · 15 citations*](https://md.research.elamur.ai/free/en/papers/handa-2024-competency-reasoning-opens-door-vulnerability/)
49. **[Safety Alignment via Constrained Knowledge Unlearning](https://md.research.elamur.ai/free/en/papers/shi-2025-safety-alignment-constrained-knowledge-unlearning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zesheng Shi, Yucheng Zhou, Jing Li, et al.*2025 · 13 citations*
50. **[VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues](https://md.research.elamur.ai/free/en/papers/zhang-2025-vlm2-bench-closer-look-how/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jianshu Zhang, Dongyu Yao, Renjie Pi, et al.*2025 · 12 citations*
51. **[AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender](https://md.research.elamur.ai/free/en/papers/zhao-2025-adasteer-your-aligned-llm-is/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Weixiang Zhao, Jiahe Guo, Yulin Hu, et al.*2025 · 11 citations*
52. [**SaRO: Enhancing LLM Safety through Reasoning-based Alignment arXiv:2504.09420**Yutao Mou, Yuxiao Luo, Shikun Zhang, et al.*2025 · 11 citations*](https://md.research.elamur.ai/free/en/papers/mou-2025-saro-enhancing-llm-safety-through/)
53. **[Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://md.research.elamur.ai/free/en/papers/hua-2026-rethinking-jailbreak-detection-large-vision/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Peichun Hua, Hao Li, Shanghao Shi, et al.*2026 · 10 citations*
54. **[Automated Progressive Red Teaming](https://md.research.elamur.ai/free/en/papers/jiang-2025-automated-progressive-red-teaming/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Bojian Jiang, Yi Jing, Tong Wu, et al.*2025 · 10 citations*
55. **[Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs](https://md.research.elamur.ai/free/en/papers/zhao-2025-beware-your-po-measuring-mitigating/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Weixiang Zhao, Yulin Hu, Yang Deng, et al.*2025 · 9 citations*
56. **[Logic Jailbreak: Efficiently Unlocking LLM Safety Restrictions Through Formal Logical Expression](https://md.research.elamur.ai/free/en/papers/peng-2026-logic-jailbreak-efficiently-unlocking-llm/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jingyu Peng, Maolin Wang, Nan Wang, et al.*2026 · 8 citations*
57. **[The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models](https://md.research.elamur.ai/free/en/papers/wu-2025-dark-side-function-calling-pathways/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Zihui Wu, Haichang Gao, Jianping He, et al.*2025 · 8 citations*
58. **[From Completion to Editing: Unlocking Context-Aware Code Infilling via Search-and-Replace Instruction Tuning](https://md.research.elamur.ai/free/en/papers/zhang-2026-completion-editing-unlocking-context-aware/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jiajun Zhang, Zeyu Cui, Jiaxi Yang, et al.*2026 · 6 citations*
59. **[GAMBIT: A Gamified Jailbreak Framework for Multimodal Large Language Models](https://md.research.elamur.ai/free/en/papers/hu-2026-gambit-gamified-jailbreak-framework-multimodal/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiangdong Hu, Yangyang Jiang, Qin Hu, et al.*2026 · 6 citations*
60. [**AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery arXiv:2604.05550**Yu Li, Chenyang Shao, Xinyang Liu, et al.*2026 · 5 citations*](https://md.research.elamur.ai/free/en/papers/li-2026-autosota-end-end-automated-research/)
61. [**MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction arXiv:2604.27393**Junbo Cui, Bokai Xu, Chongyi Wang, et al.*2026 · 5 citations*](https://md.research.elamur.ai/free/en/papers/cui-2026-minicpm-o-4-5/)
62. **[HAUNTATTACK: When Attack Follows Reasoning as a Shadow](https://md.research.elamur.ai/free/en/papers/ma-2026-hauntattack-when-attack-follows-reasoning/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jingyuan Ma, Rui Li, Zheng Li, et al.*2026 · 3 citations*
63. **[Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?](https://md.research.elamur.ai/free/en/papers/xin-2026-jailbreaking-attacks-vs-content-safety/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yuan Xin, Dingfan Chen, Linyi Yang, et al.*2026 · 3 citations*
64. **[SafeMT: Multi-turn Safety for Multimodal Language Models](https://md.research.elamur.ai/free/en/papers/zhu-2026-safemt-multi-turn-safety-multimodal/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Han Zhu, Juntao Dai, Jiaming Ji, et al.*2026 · 3 citations*
65. **[ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback](https://md.research.elamur.ai/free/en/papers/mou-2026-toolsafe-enhancing-tool-invocation-safety/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yutao Mou, Zhangchi Xue, Lijun Li, et al.*2026 · 3 citations*
66. **[Universal Jailbreak Suffixes Are Strong Attention Hijackers](https://md.research.elamur.ai/free/en/papers/tov-2026-universal-jailbreak-suffixes-are-strong/) [Transactions of the Association for Computational Linguistics (TACL)](https://md.research.elamur.ai/free/en/venues/tacl/)**Matan Ben-Tov, Mor Geva, Mahmood Sharif*2026 · 3 citations*
67. **[Unraveling LLM Jailbreaks Through Safety Knowledge Neurons](https://md.research.elamur.ai/free/en/papers/zhao-2026-unraveling-llm-jailbreaks-through-safety/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Chongwen Zhao, Yutong Ke, Kaizhu Huang*2026 · 3 citations*
68. **[Are LLMs Reliable Rankers? Rank Manipulation via Two-Stage Token Optimization](https://md.research.elamur.ai/free/en/papers/xing-2026-are-llms-reliable-rankers-rank/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Tiancheng Xing, Jerry Li, Yixuan Du, et al.*2026 · 2 citations*
69. **[Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World](https://md.research.elamur.ai/free/en/papers/sadasivan-2026-attacker-s-noise-can-manipulate/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Vinu Sankar Sadasivan, Soheil Feizi, Rajiv Mathews, et al.*2026 · 2 citations*
70. **[In-Context Representation Hijacking](https://md.research.elamur.ai/free/en/papers/yona-2026-context-representation-hijacking/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Itay Yona, Amir Sarid, Michael Karasik, et al.*2026 · 2 citations*
71. **[Persona Jailbreaking in Large Language Models](https://md.research.elamur.ai/free/en/papers/sandhan-2026-persona-jailbreaking-large-language-models/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jivnesh Sandhan, Fei Cheng, Tushar Sandhan, et al.*2026 · 2 citations*
72. **[PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics](https://md.research.elamur.ai/free/en/papers/shen-2026-psychethicsbench-evaluating-large-language-models/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yaling Shen, Stephanie Fong, Yiwen Jiang, et al.*2026 · 2 citations*
73. **[Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts](https://md.research.elamur.ai/free/en/papers/ziakas-2026-red-bandit-test-time-adaptation/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Christos Ziakas, Nicholas Loo, Nishita Jain, et al.*2026 · 2 citations*
74. **[RedCoder: Automated Multi-Turn Red Teaming for Code LLMs](https://md.research.elamur.ai/free/en/papers/mo-2026-redcoder-automated-multi-turn-red/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, et al.*2026 · 2 citations*
75. **[XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants](https://md.research.elamur.ai/free/en/papers/storek-2026-xoxo-stealthy-cross-origin-context/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Adam Štorek, Mukur Gupta, Noopur Bhatt, et al.*2026 · 2 citations*
76. **[Activation-Guided Local Editing for Jailbreaking Attacks](https://md.research.elamur.ai/free/en/papers/wang-2026-activation-guided-local-editing-jailbreaking/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jiecong Wang, Haoran Li, Hao Peng, et al.*2026 · 1 citation*
77. **[Adversarial Decoding: Generating Readable Documents for Adversarial Objectives](https://md.research.elamur.ai/free/en/papers/zhang-2026-adversarial-decoding-generating-readable-documents/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Collin Zhang, Tingwei Zhang, Vitaly Shmatikov*2026 · 1 citation*
78. **[Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay](https://md.research.elamur.ai/free/en/papers/wang-2026-be-your-own-red-teamer/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Hao Wang, Yanting Wang, Hao Li, et al.*2026 · 1 citation*
79. **[Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning](https://md.research.elamur.ai/free/en/papers/pu-2026-beyond-surface-level-detection-cognitive/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Rui Pu, Chaozhuo Li, Rui Ha, et al.*2026 · 1 citation*
80. **[BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage](https://md.research.elamur.ai/free/en/papers/nakka-2026-bitbypass-new-direction-jailbreaking-aligned/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Kalyan Nakka, Nitesh Saxena*2026 · 1 citation*
81. **[From Attack Surfaces to Actual Operations: A Survey of Modern LLM Jailbreaks](https://md.research.elamur.ai/free/en/papers/zhou-2026-attack-surfaces-actual-operations-survey/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Ruikang Zhou, Changsheng Sun, Mark Huasong Meng*2026 · 1 citation*
82. **[Reasoning Up the Instruction Ladder for Controllable Language Models](https://md.research.elamur.ai/free/en/papers/zheng-2026-reasoning-up-instruction-ladder-controllable/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Zishuo Zheng, Vidhisha Balachandran, Chan Young Park, et al.*2026 · 1 citation*
83. **[Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models](https://md.research.elamur.ai/free/en/papers/zhao-2026-unleashing-unseen-harnessing-benign-datasets/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Wei Zhao, Zhe Li, Yige Li, et al.*2026 · 1 citation*
84. **[USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS](https://md.research.elamur.ai/free/en/papers/zheng-2026-usb-comprehensive-unified-safety-evaluation/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Baolin Zheng, Guanlin Chen, Qingyang Teng, et al.*2026 · 1 citation*
85. **[When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life](https://md.research.elamur.ai/free/en/papers/lou-2026-when-helpers-become-hazards-benchmark/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Xinyue Lou, Xu Jinan, Jingyi Yin, et al.*2026 · 1 citation*
86. [**HAMSA: Hijacking Aligned Compact Models via Stealthy Automation arXiv:2508.16484**Alexey Krylov, Iskander Vagizov, Dmitrii Korzh, et al.*2025 · 1 citation*](https://md.research.elamur.ai/free/en/papers/krylov-2025-hamsa-hijacking-aligned-compact-models/)
87. **[CachePrune: Teaching LLMs What Not to Follow via KV-Cache Editing](https://md.research.elamur.ai/free/en/papers/wang-2026-cacheprune-teaching-llms-what-not/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Rui Wang, Junda Wu, Yu Xia, et al.*2026*
88. **[Calibrating Inference Time Alignment with Sequence-level Risk Accumulation](https://md.research.elamur.ai/free/en/papers/tan-2026-calibrating-inference-time-alignment-sequence/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Shanwen Tan, Ziyang Dong, Wei Ju, et al.*2026*
89. **[Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring](https://md.research.elamur.ai/free/en/papers/luo-2026-detecting-what-queries-seek-steering/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiaohao Luo, Ying Wei, Rui Zhao*2026*
90. **[Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance](https://md.research.elamur.ai/free/en/papers/wang-2026-enhancing-transferability-jailbreak-attacks-large/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Ao Wang, Xinghao Yang, Yongshun Gong, et al.*2026*
91. **[Evaluating Discriminability of Vision-Language Models](https://md.research.elamur.ai/free/en/papers/muraoka-2026-evaluating-discriminability-vision-language-models/) [Language Resources and Evaluation Conference (LREC)](https://md.research.elamur.ai/free/en/venues/lrec/)**Masayasu Muraoka, Naoaki Okazaki*2026*
92. **[Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment](https://md.research.elamur.ai/free/en/papers/song-2026-hard-read-easy-jailbreak-how/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Zhixue Song, Boyan Han, Yiwei Wang, et al.*2026*
93. **[Jailbreaking Large Language Models with Morality Attacks](https://md.research.elamur.ai/free/en/papers/su-2026-jailbreaking-large-language-models-morality/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Ying Su, Zheng Mingen, Weili Diao, et al.*2026*
94. **[LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks](https://md.research.elamur.ai/free/en/papers/wan-2026-lco-llm-based-constraint-optimization/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Jiayong Wan, Jiawei Chen, Zhaoxia Yin, et al.*2026*
95. **[MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models](https://md.research.elamur.ai/free/en/papers/makwana-2026-mlingualfc-evaluating-jailbreak-vulnerabilities-multilingual/) [Workshop on Multilinguality in the Era of Large Language Models](https://md.research.elamur.ai/free/en/venues/mellm/)**Rishabh Makwana, Mamta Mamta, Deeksha Varshney, et al.*2026*
96. **[More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters](https://md.research.elamur.ai/free/en/papers/wang-2026-more-thinking-less-talking-internalizing/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Guan Wang, Xuehai Tang, Biyu Zhou, et al.*2026*
97. **[PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage](https://md.research.elamur.ai/free/en/papers/nakka-2026-pii-jailbreaking-llms-activation-steering/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Krishna Kanth Nakka, Xue Jiang, Dmitrii Usynin, et al.*2026*
98. **[PII-VisBench: Evaluating Personally Identifiable Information Safety in Vision Language Models Along a Continuum of Visibility](https://md.research.elamur.ai/free/en/papers/shahariar-2026-pii-visbench-evaluating-personally-identifiable/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**G M Shahariar, Zabir Al Nazi, Md Olid Hasan Bhuiyan, et al.*2026*
99. **[Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs](https://md.research.elamur.ai/free/en/papers/si-2026-pruning-unsafe-tickets-resource-efficient/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Wai Man Si, Mingjie Li, Michael Backes, et al.*2026*
100. **[RAMP: Risk-Aware Multi-Turn Planning for Jailbreak Red-Teaming](https://md.research.elamur.ai/free/en/papers/liu-2026-ramp-risk-aware-multi-turn/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Yize Liu, Yunyun Hou, Aina Sui*2026*

**1** [2](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/cited-by/page/2/) [next →](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/cited-by/page/2/)

- [← back to](https://md.research.elamur.ai/free/en/authors/xiaogeng-liu/) — Xiaogeng Liu