English
Related papers

Related papers: Investigating Adversarial Trigger Transfer in Larg…

200 papers

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…

Computation and Language · Computer Science 2023-12-22 Andy Zou , Zifan Wang , Nicholas Carlini , Milad Nasr , J. Zico Kolter , Matt Fredrikson

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Machine Learning (ML) models are known to be vulnerable to adversarial inputs and researchers have demonstrated that even production systems, such as self-driving cars and ML-as-a-service offerings, are susceptible. These systems represent…

Machine Learning · Computer Science 2021-01-11 Marissa Dotter , Sherry Xie , Keith Manville , Josh Harguess , Colin Busho , Mikel Rodriguez

Transfer-based attack adopts the adversarial examples generated on the surrogate model to attack various models, making it applicable in the physical world and attracting increasing interest. Recently, various adversarial attacks have…

Computer Vision and Pattern Recognition · Computer Science 2023-11-03 Zhijin Ge , Hongying Liu , Xiaosen Wang , Fanhua Shang , Yuanyuan Liu

Federated learning allows for clients in a distributed system to jointly train a machine learning model. However, clients' models are vulnerable to attacks during the training and testing phases. In this paper, we address the issue of…

Machine Learning · Computer Science 2023-10-24 Taejin Kim , Shubhranshu Singh , Nikhil Madaan , Carlee Joe-Wong

Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…

Computation and Language · Computer Science 2026-04-29 Shirin Alanova , Bogdan Minko , Sabrina Sadiekh , Evgeniy Kokuykin

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Machine Learning · Computer Science 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better…

Machine Learning · Computer Science 2021-11-09 Zhuolin Yang , Linyi Li , Xiaojun Xu , Shiliang Zuo , Qian Chen , Benjamin Rubinstein , Pan Zhou , Ce Zhang , Bo Li

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Computation and Language · Computer Science 2021-12-23 Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Machine Learning · Computer Science 2024-04-04 Nandish Chattopadhyay , Atreya Goswami , Anupam Chattopadhyay

Model providers increasingly release open weights or allow users to fine-tune foundation models through APIs. Although these models are safety-aligned before release, their safeguards can often be removed by fine-tuning on harmful data.…

Cryptography and Security · Computer Science 2026-05-26 Itay Zloczower , Eyal Lenga , Gilad Gressel , Yisroel Mirsky

Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a…

Machine Learning · Statistics 2019-01-30 Sanjay Kariyappa , Moinuddin K. Qureshi

Jailbreak attacks against large language models (LLMs) aim to induce harmful behaviors in LLMs through carefully crafted adversarial prompts. To mitigate attacks, one way is to perform adversarial training (AT)-based alignment, i.e.,…

Machine Learning · Computer Science 2026-02-03 Shaopeng Fu , Liang Ding , Jingfeng Zhang , Di Wang

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning. Variants of this method have been used as regularization mechanisms to achieve SOTA results on NLP benchmarks, and…

Computation and Language · Computer Science 2021-09-30 Javid Ebrahimi , Hao Yang , Wei Zhang

Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…

Machine Learning · Computer Science 2026-04-02 Aengus Lynch

Jailbreaking attacks on large language models pose a significant threat to AI safety by enabling the generation of harmful or restricted content. While prior work has explored both handcrafted and automated jailbreak strategies, the…

Cryptography and Security · Computer Science 2026-05-18 Reinelle Jan Bugnot , Soohyeon Choi , Hoon Wei Lim , Yue Duan

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

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Machine Learning · Computer Science 2022-05-03 Yang Li , Quan Pan , Erik Cambria

Large language models (LLMs) are improving at an exceptional rate. However, these models are still susceptible to jailbreak attacks, which are becoming increasingly dangerous as models become increasingly powerful. In this work, we…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Cryptography and Security · Computer Science 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das