English
Related papers

Related papers: BadGPT-4o: stripping safety finetuning from GPT mo…

200 papers

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Recent advancements in large language models (LLMs) have underscored their vulnerability to safety alignment jailbreaks, particularly when subjected to downstream fine-tuning. However, existing mitigation strategies primarily focus on…

Cryptography and Security · Computer Science 2025-06-06 Lei Hsiung , Tianyu Pang , Yung-Chen Tang , Linyue Song , Tsung-Yi Ho , Pin-Yu Chen , Yaoqing Yang

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the…

Cryptography and Security · Computer Science 2025-02-06 Xunguang Wang , Daoyuan Wu , Zhenlan Ji , Zongjie Li , Pingchuan Ma , Shuai Wang , Yingjiu Li , Yang Liu , Ning Liu , Juergen Rahmel

As large language models (LLMs) become integrated into everyday applications, ensuring their robustness and security is increasingly critical. In particular, LLMs can be manipulated into unsafe behaviour by prompts known as jailbreaks. The…

Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack success rate using dictionary-based evaluation, existing…

Cryptography and Security · Computer Science 2025-04-14 Tianyi Wu , Zhiwei Xue , Yue Liu , Jiaheng Zhang , Bryan Hooi , See-Kiong Ng

Existing black-box jailbreak attacks achieve certain success on non-reasoning models but degrade significantly on recent SOTA reasoning models. To improve attack ability, inspired by adversarial aggregation strategies, we integrate multiple…

Computation and Language · Computer Science 2026-01-08 Chiyu Zhang , Lu Zhou , Xiaogang Xu , Jiafei Wu , Liming Fang , Zhe Liu

The inherent risk of generating harmful and unsafe content by Large Language Models (LLMs), has highlighted the need for their safety alignment. Various techniques like supervised fine-tuning, reinforcement learning from human feedback, and…

Cryptography and Security · Computer Science 2026-03-04 Kalyan Nakka , Nitesh Saxena

Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause…

Computation and Language · Computer Science 2025-01-07 Joao Fonseca , Andrew Bell , Julia Stoyanovich

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Yunhan Zhao , Xiang Zheng , Xingjun Ma

As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…

Machine Learning · Computer Science 2025-10-08 Jaiden Fairoze , Sanjam Garg , Keewoo Lee , Mingyuan Wang

As large language models (LLMs) are increasingly fine-tuned for hardware tasks like RTL code generation, the scarcity of high-quality datasets often leads to the use of rapidly assembled or generated training data. These datasets frequently…

Cryptography and Security · Computer Science 2026-05-01 Mahshid Rezakhani , Nowfel Mashnoor , Kimia Azar , Hadi Kamali

This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts…

Cryptography and Security · Computer Science 2026-05-12 Zheng Lin , Zhenxing Niu , Haoxuan Ji , Yuzhe Huang , Haichang Gao

The rise of Generative AI (GenAI) has reshaped the cybersecurity landscape by enabling new attack vectors and lowering the barrier for executing advanced social engineering campaigns. This study conducts an empirical analysis of…

Cryptography and Security · Computer Science 2026-04-02 Rina Mishra , Gaurav Varshney

Ensuring the safety and alignment of large language models (LLMs) with human values is crucial for generating responses that are beneficial to humanity. While LLMs have the capability to identify and avoid harmful queries, they remain…

Computation and Language · Computer Science 2024-10-22 Yihua Zhou , Xiaochuan Shi

Despite significant ongoing efforts in safety alignment, large language models (LLMs) such as GPT-4 and LLaMA 3 remain vulnerable to jailbreak attacks that can induce harmful behaviors, including through the use of adversarial suffixes.…

Cryptography and Security · Computer Science 2024-12-20 Wei Zhao , Zhe Li , Yige Li , Jun Sun

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same…

Cryptography and Security · Computer Science 2026-02-27 Piyush Jaiswal , Aaditya Pratap , Shreyansh Saraswati , Harsh Kasyap , Somanath Tripathy

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for defending against jailbreak attacks are primarily based on auxiliary models. These strategies, however, often require extensive data collection or…

Cryptography and Security · Computer Science 2025-11-21 Zhuoran Yang , Yanyong Zhang

Optimization-based jailbreaks typically adopt the Toxic-Continuation setting in large vision-language models (LVLMs), following the standard next-token prediction objective. In this setting, an adversarial image is optimized to make the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Hee-Seon Kim , Minbeom Kim , Wonjun Lee , Kihyun Kim , Changick Kim

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

Cryptography and Security · Computer Science 2026-05-05 Yi Yang , Jinyang Huang , Binbin Liu , Feng-Qi Cui , Xiaokang Zhou , Zhi Liu , Jie Zhang , Meng Li

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits in model parameters. Our attack jailbreaks billion-parameter…

Cryptography and Security · Computer Science 2025-10-06 Zachary Coalson , Jeonghyun Woo , Chris S. Lin , Joyce Qu , Yu Sun , Shiyang Chen , Lishan Yang , Gururaj Saileshwar , Prashant Nair , Bo Fang , Sanghyun Hong