English
Related papers

Related papers: Jailbreak Transferability Emerges from Shared Repr…

200 papers

Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from…

Artificial Intelligence · Computer Science 2025-09-30 Zhaoqi Wang , Daqing He , Zijian Zhang , Xin Li , Liehuang Zhu , Meng Li , Jiamou Liu

Transfer-based adversarial attacks can evaluate model robustness in the black-box setting. Several methods have demonstrated impressive untargeted transferability, however, it is still challenging to efficiently produce targeted…

Machine Learning · Computer Science 2022-07-25 Xiao Yang , Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

Model Merging (MM) has emerged as a promising alternative to multi-task learning, where multiple fine-tuned models are combined, without access to tasks' training data, into a single model that maintains performance across tasks. Recent…

Machine Learning · Computer Science 2025-09-30 Ankit Gangwal , Aaryan Ajay Sharma

Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…

Computation and Language · Computer Science 2024-03-28 Abhinav Rao , Sachin Vashistha , Atharva Naik , Somak Aditya , Monojit Choudhury

Evaluating and mitigating a generative system's susceptibility to jailbreak attacks is critical to its safe deployment. Given the number of deployable systems, full per-configuration evaluation and optimization is impractical. In this…

Cryptography and Security · Computer Science 2026-05-27 Hayden Helm , Xiaodong Liu , Weiwei Yang

Large Language Models (LLMs) have revolutionized artificial intelligence, demonstrating remarkable computational power and linguistic capabilities. However, these models are inherently prone to various biases stemming from their training…

Computation and Language · Computer Science 2025-02-14 Riccardo Cantini , Giada Cosenza , Alessio Orsino , Domenico Talia

Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black-box attacks…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Yinpeng Dong , Tianyu Pang , Hang Su , Jun Zhu

Large Language Models (LLMs) have become increasingly popular for their advanced text generation capabilities across various domains. However, like any software, they face security challenges, including the risk of 'jailbreak' attacks that…

Cryptography and Security · Computer Science 2024-01-31 Jie Li , Yi Liu , Chongyang Liu , Ling Shi , Xiaoning Ren , Yaowen Zheng , Yang Liu , Yinxing Xue

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Cryptography and Security · Computer Science 2024-12-03 Erick Galinkin , Martin Sablotny

The transferability of adversarial examples is a key issue in the security of deep neural networks. The possibility of an adversarial example crafted for a source model fooling another targeted model makes the threat of adversarial attacks…

Cryptography and Security · Computer Science 2023-07-18 Thibault Maho , Seyed-Mohsen Moosavi-Dezfooli , Teddy Furon

Model ensemble adversarial attack has become a powerful method for generating transferable adversarial examples that can target even unknown models, but its theoretical foundation remains underexplored. To address this gap, we provide early…

Machine Learning · Computer Science 2025-05-29 Wei Yao , Zeliang Zhang , Huayi Tang , Yong Liu

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Cryptography and Security · Computer Science 2025-06-10 Yukai Zhou , Sibei Yang , Wenjie Wang

Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of…

Machine Learning · Computer Science 2020-05-13 George Adam , Romain Speciel

Large (vision-)language models exhibit remarkable capability but remain highly susceptible to jailbreaking. Existing safety training approaches aim to have the model learn a refusal boundary between safe and unsafe, based on the user's…

Cryptography and Security · Computer Science 2026-04-28 Xinhe Wang , Katia Sycara , Yaqi Xie

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Jailbreaking is an essential adversarial technique for red-teaming these models to uncover and patch security flaws. However, existing jailbreak methods face significant drawbacks. Token-level jailbreak attacks often produce incoherent or…

Cryptography and Security · Computer Science 2026-04-16 Jiecong Wang , Haoran Li , Hao Peng , Ziqian Zeng , Zihao Wang , Haohua Du , Zhengtao Yu

We find that language models have difficulties generating fallacious and deceptive reasoning. When asked to generate deceptive outputs, language models tend to leak honest counterparts but believe them to be false. Exploiting this…

Computation and Language · Computer Science 2025-05-26 Yue Zhou , Henry Peng Zou , Barbara Di Eugenio , Yang Zhang

Adversarial attacks against Deep Neural Networks have been widely studied. One significant feature that makes such attacks particularly powerful is transferability, where the adversarial examples generated from one model can be effective…

Cryptography and Security · Computer Science 2020-09-29 Renzhi Wang , Tianwei Zhang , Xiaofei Xie , Lei Ma , Cong Tian , Felix Juefei-Xu , Yang Liu

Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Zhipeng Wei , Jingjing Chen , Zuxuan Wu , Yu-Gang Jiang