"jailbreaking attacks" Papers

15 papers found

Filters:jailbreaking attacksClear all

Conference

AAAI 2025 (3,028)COLM 2025 (418)CVPR 2025 (2,873)ICCV 2025 (2,701)ICLR 2025 (3,827)ICML 2025 (3,340)ISMAR 2025 (229)NEURIPS 2025 (5,858)AAAI 2024 (2,289)CVPR 2024 (2,716)ECCV 2024 (2,387)ICLR 2024 (2,297)ICML 2024 (2,635)

Paper Type

poster (24,624)paper (8,558)oral (1,594)spotlight (1,421)highlight (975)

$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning

Mintong Kang, Bo Li

ICLR 2025arXiv:2407.05557
34
citations

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Anselm Paulus, Arman Zharmagambetov, Chuan Guo et al.

ICML 2025arXiv:2404.16873
132
citations

Attention! Your Vision Language Model Could Be Maliciously Manipulated

Xiaosen Wang, Shaokang Wang, Zhijin Ge et al.

NEURIPS 2025arXiv:2505.19911
3
citations

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Hangtao Zhang, Chenyu Zhu, Xianlong Wang et al.

ICLR 2025
6
citations

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models

Seanie Lee, Haebin Seong, Dong Bok Lee et al.

ICLR 2025arXiv:2410.01524
15
citations

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Maksym Andriushchenko, francesco croce, Nicolas Flammarion

ICLR 2025arXiv:2404.02151
401
citations

Lifelong Safety Alignment for Language Models

Haoyu Wang, Yifei Zhao, Zeyu Qin et al.

NEURIPS 2025arXiv:2505.20259
7
citations

Persistent Pre-training Poisoning of LLMs

Yiming Zhang, Javier Rando, Ivan Evtimov et al.

ICLR 2025arXiv:2410.13722
38
citations

ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs

Hao Di, Tong He, Haishan Ye et al.

ICLR 2025
2
citations

Understanding and Enhancing the Transferability of Jailbreaking Attacks

Runqi Lin, Bo Han, Fengwang Li et al.

ICLR 2025arXiv:2502.03052
18
citations

Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications

Boyi Wei, Kaixuan Huang, Yangsibo Huang et al.

ICML 2024arXiv:2402.05162
184
citations

Fast Adversarial Attacks on Language Models In One GPU Minute

Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan et al.

ICML 2024arXiv:2402.15570
72
citations

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content

Zhuowen Yuan, Zidi Xiong, Yi Zeng et al.

ICML 2024arXiv:2403.13031
67
citations

Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Yongshuo Zong, Ondrej Bohdal, Tingyang Yu et al.

ICML 2024arXiv:2402.02207
123
citations

The First to Know: How Token Distributions Reveal Hidden Knowledge in Large Vision-Language Models?

Qinyu Zhao, Ming Xu, Kartik Gupta et al.

ECCV 2024arXiv:2403.09037
15
citations