English
Related papers

Related papers: Context is the Key: Backdoor Attacks for In-Contex…

200 papers

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Cryptography and Security · Computer Science 2026-02-17 Anudeep Das , Prach Chantasantitam , Gurjot Singh , Lipeng He , Mariia Ponomarenko , Florian Kerschbaum

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Zhiyuan Zhong , Zhen Sun , Yepang Liu , Xinlei He , Guanhong Tao

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation during training and evaluation. Since data used in these…

Cryptography and Security · Computer Science 2024-12-25 Sara Price , Arjun Panickssery , Sam Bowman , Asa Cooper Stickland

Large language models (LLMs) have recently shown great potential for in-context learning, where LLMs learn a new task simply by conditioning on a few input-label pairs (prompts). Despite their potential, our understanding of the factors…

Computation and Language · Computer Science 2023-09-12 Ruixiang Tang , Dehan Kong , Longtao Huang , Hui Xue

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…

Cryptography and Security · Computer Science 2024-10-08 Lu Yan , Siyuan Cheng , Xuan Chen , Kaiyuan Zhang , Guangyu Shen , Zhuo Zhang , Xiangyu Zhang

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teacher} models over large datasets via fine-tuning. Many…

Machine Learning · Computer Science 2020-08-11 Shuo Wang , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen , Tianle Chen

Malicious agents in collaborative learning and outsourced data collection threaten the training of clean models. Backdoor attacks, where an attacker poisons a model during training to successfully achieve targeted misclassification, are a…

Machine Learning · Computer Science 2022-01-31 Siddhartha Datta , Nigel Shadbolt

Prompts have significantly improved the performance of pretrained Large Language Models (LLMs) on various downstream tasks recently, making them increasingly indispensable for a diverse range of LLM application scenarios. However, the…

Computation and Language · Computer Science 2023-12-19 Hongwei Yao , Jian Lou , Zhan Qin

Recent research has confirmed the feasibility of backdoor attacks in deep reinforcement learning (RL) systems. However, the existing attacks require the ability to arbitrarily modify an agent's observation, constraining the application…

Cryptography and Security · Computer Science 2021-12-14 Lun Wang , Zaynah Javed , Xian Wu , Wenbo Guo , Xinyu Xing , Dawn Song

Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid progress in multimodal understanding. Despite these achievements, the security of VLMs,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Nam Duong Tran , Phi Le Nguyen

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised…

Computation and Language · Computer Science 2023-05-29 Xuanli He , Jun Wang , Benjamin Rubinstein , Trevor Cohn

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zhifang Zhang , Bojun Yang , Shuo He , Weitong Chen , Wei Emma Zhang , Olaf Maennel , Lei Feng , Miao Xu

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Cryptography and Security · Computer Science 2026-04-22 Kun Wang , Cheng Qian , Miao Yu , Lilan Peng , Liang Lin , Jiaming Zhang , Tianyu Zhang , Yu Cheng , Yang Wang

Large transformer models trained on diverse datasets have shown a remarkable ability to learn in-context, achieving high few-shot performance on tasks they were not explicitly trained to solve. In this paper, we study the in-context…

Machine Learning · Computer Science 2023-06-27 Jonathan N. Lee , Annie Xie , Aldo Pacchiano , Yash Chandak , Chelsea Finn , Ofir Nachum , Emma Brunskill

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Cryptography and Security · Computer Science 2025-10-07 Chenyu Wang , Zhou Yang , Yaniv Harel , David Lo

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

Cryptography and Security · Computer Science 2021-02-22 Eugene Bagdasaryan , Vitaly Shmatikov

The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent complexity of deep learning models, while contributing to…

Cryptography and Security · Computer Science 2025-01-08 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Cryptography and Security · Computer Science 2019-06-05 Jiazhu Dai , Chuanshuai Chen

Large-scale models trained on broad data have recently become the mainstream architecture in computer vision due to their strong generalization performance. In this paper, the main focus is on an emergent ability in large vision models,…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Yuanhan Zhang , Kaiyang Zhou , Ziwei Liu