English
Related papers

Related papers: Token-Level Constraint Boundary Search for Jailbre…

200 papers

Deep learning systems are known to be vulnerable to adversarial examples. In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the network by submitting…

Cryptography and Security · Computer Science 2022-06-10 Huiying Li , Shawn Shan , Emily Wenger , Jiayun Zhang , Haitao Zheng , Ben Y. Zhao

We introduce a novel framework for consolidating multi-turn adversarial ``jailbreak'' prompts into single-turn queries, significantly reducing the manual overhead required for adversarial testing of large language models (LLMs). While…

Computation and Language · Computer Science 2025-08-06 Junwoo Ha , Hyunjun Kim , Sangyoon Yu , Haon Park , Ashkan Yousefpour , Yuna Park , Suhyun Kim

Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and harmful content raises…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Changhoon Kim , Yanjun Qi

Large language models (LLMs) are known to be vulnerable to jailbreak attacks, which typically rely on carefully designed prompts containing explicit semantic structure. These attacks generally operate by fixing an adversarial instruction…

Machine Learning · Computer Science 2026-05-07 Marco Rando , Samuel Vaiter

End-to-end encryption (E2EE) by messaging platforms enable people to securely and privately communicate with one another. Its widespread adoption however raised concerns that illegal content might now be shared undetected. Following the…

Cryptography and Security · Computer Science 2022-08-03 Shubham Jain , Ana-Maria Cretu , Yves-Alexandre de Montjoye

With the rise of text-to-image (T2I) generative AI models reaching wide audiences, it is critical to evaluate model robustness against non-obvious attacks to mitigate the generation of offensive images. By focusing on ``implicitly…

While large language models (LLMs) exhibit remarkable capabilities across various tasks, they encounter potential security risks such as jailbreak attacks, which exploit vulnerabilities to bypass security measures and generate harmful…

Cryptography and Security · Computer Science 2024-11-28 Xinyuan Wang , Victor Shea-Jay Huang , Renmiao Chen , Hao Wang , Chengwei Pan , Lei Sha , Minlie Huang

Recent text-to-image (T2I) models have had great success, and many benchmarks have been proposed to evaluate their performance and safety. However, they only consider explicit prompts while neglecting implicit prompts (hint at a target…

Computers and Society · Computer Science 2024-05-29 Yue Yang , Yuqi Lin , Hong Liu , Wenqi Shao , Runjian Chen , Hailong Shang , Yu Wang , Yu Qiao , Kaipeng Zhang , Ping Luo

Adversarial text attack research plays a crucial role in evaluating the robustness of NLP models. However, the increasing complexity of transformer-based architectures has dramatically raised the computational cost of attack testing,…

Computation and Language · Computer Science 2025-09-26 Abhinay Shankar Belde , Rohit Ramkumar , Jonathan Rusert

Large Language Models (LLMs) exhibit impressive capabilities yet suffer from sensitivity to slight input context variations, hampering reliability. Conventional metrics like accuracy and perplexity fail to assess local prediction…

Computation and Language · Computer Science 2026-02-12 Deyuan Liu , Zecheng Wang , Zhanyue Qin , Zhiying Tu , Dianhui Chu , Dianbo Sui

The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of…

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

Cryptography and Security · Computer Science 2025-08-14 Boyuan Chen , Minghao Shao , Abdul Basit , Siddharth Garg , Muhammad Shafique

Large Language Models (LLMs) are increasingly susceptible to jailbreak attacks, which are adversarial prompts that bypass alignment constraints and induce unauthorized or harmful behaviors. These vulnerabilities undermine the safety,…

Machine Learning · Computer Science 2025-09-30 Javad Forough , Mohammad Maheri , Hamed Haddadi

As Text-to-Image (T2I) generation becomes widespread, third-party platforms increasingly integrate multiple model APIs for convenient image creation. However, false claims of using official models can mislead users and harm model owners'…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Zidong Zhao , Yihao Huang , Qing Guo , Tianlin Li , Anran Li , Kailong Wang , Jin Song Dong , Geguang Pu

Aligning Text-to-Image (T2I) generation models with human preferences increasingly relies on image reward models that score or rank generated images according to prompt alignment and perceptual quality. Existing reward models are commonly…

Artificial Intelligence · Computer Science 2026-05-22 Kuei-Chun Kao , Daixuan Huo , Yuanhao Ban , Cho-Jui Hsieh

Recent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial robustness of VLMs has not been fully explored. Existing methods mainly assess robustness…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Ruofan Wang , Xingjun Ma , Hanxu Zhou , Chuanjun Ji , Guangnan Ye , Yu-Gang Jiang

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

Cryptography and Security · Computer Science 2026-05-18 Jiate Li , Defu Cao , Li Li , Wei Yang , Yuehan Qin , Chenxiao Yu , Tiannuo Yang , Ryan A. Rossi , Yan Liu , Xiyang Hu , Yue Zhao

Backdoor attacks have become a major security threat for deploying machine learning models in security-critical applications. Existing research endeavors have proposed many defenses against backdoor attacks. Despite demonstrating certain…

Machine Learning · Computer Science 2023-11-28 Hengzhi Pei , Jinyuan Jia , Wenbo Guo , Bo Li , Dawn Song

Existing large language models (LLMs) are advancing rapidly and produce outstanding results in image generation tasks, yet their content safety checks remain vulnerable to prompt-based jailbreaks. Through preliminary testing on platforms…

Computation and Language · Computer Science 2025-05-08 Variath Madhupal Gautham Nair , Vishal Varma Dantuluri

The widespread use of Text-to-Image (T2I) models in content generation requires careful examination of their safety, including their robustness to adversarial attacks. Despite extensive research on adversarial attacks, the reasons for their…

Machine Learning · Computer Science 2024-07-18 Haz Sameen Shahgir , Xianghao Kong , Greg Ver Steeg , Yue Dong