English
Related papers

Related papers: Instance-Level Trojan Attacks on Visual Question A…

200 papers

This paper proposes MergeGuard, a novel methodology for mitigation of AI Trojan attacks. Trojan attacks on AI models cause inputs embedded with triggers to be misclassified to an adversary's target class, posing a significant threat to…

Cryptography and Security · Computer Science 2025-05-08 Soheil Zibakhsh Shabgahi , Yaman Jandali , Farinaz Koushanfar

Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded attack surfaces, thereby exposing them to novel security…

Computation and Language · Computer Science 2025-05-29 Juan Ren , Mark Dras , Usman Naseem

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Cryptography and Security · Computer Science 2025-09-10 Bilal Hussain Abbasi , Yanjun Zhang , Leo Zhang , Shang Gao

Benefiting from large-scale pre-training, we have witnessed significant performance boost on the popular Visual Question Answering (VQA) task. Despite rapid progress, it remains unclear whether these state-of-the-art (SOTA) models are…

Computer Vision and Pattern Recognition · Computer Science 2021-08-16 Linjie Li , Jie Lei , Zhe Gan , Jingjing Liu

In typical multimodal tasks, such as Visual Question Answering (VQA), adversarial attacks targeting a specific image and question can lead large vision-language models (LVLMs) to provide incorrect answers. However, it is common for a single…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Yudong Zhang , Ruobing Xie , Jiansheng Chen , Xingwu Sun , Zhanhui Kang , Yu Wang

Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan…

Computer Vision and Pattern Recognition · Computer Science 2020-07-30 Xiaoyu Zhang , Ajmal Mian , Rohit Gupta , Nazanin Rahnavard , Mubarak Shah

Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correlates well with the qualitative assessment of the attacks. We…

Computer Vision and Pattern Recognition · Computer Science 2018-06-13 George Gondim-Ribeiro , Pedro Tabacof , Eduardo Valle

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

Machine Learning · Computer Science 2023-02-28 You Qiaoben , Chengyang Ying , Xinning Zhou , Hang Su , Jun Zhu , Bo Zhang

Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant role, leaving the user role unaligned, and stick to a fixed…

Cryptography and Security · Computer Science 2025-04-08 Erfan Shayegani , G M Shahariar , Sara Abdali , Lei Yu , Nael Abu-Ghazaleh , Yue Dong

Deep Neural Networks (DNNs) have been shown to be susceptible to Trojan attacks. Neural Trojan is a type of targeted poisoning attack that embeds the backdoor into the victim and is activated by the trigger in the input space. The…

Machine Learning · Computer Science 2022-08-11 Diego Garcia-soto , Huili Chen , Farinaz Koushanfar

Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs)…

Machine Learning · Computer Science 2017-01-17 Vahid Behzadan , Arslan Munir

The deep neural network (DNN) models for object detection using camera images are widely adopted in autonomous vehicles. However, DNN models are shown to be susceptible to adversarial image perturbations. In the existing methods of…

Robotics · Computer Science 2023-03-17 Hyung-Jin Yoon , Hamidreza Jafarnejadsani , Petros Voulgaris

Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial examples for vision and language models, which incorporate…

Artificial Intelligence · Computer Science 2018-04-09 Xiaojun Xu , Xinyun Chen , Chang Liu , Anna Rohrbach , Trevor Darrell , Dawn Song

Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which includes the trigger. With the increasing relevance of deep…

Machine Learning · Computer Science 2025-12-16 Xihe Gu , Greg Fields , Yaman Jandali , Tara Javidi , Farinaz Koushanfar

Deep learning underpins most of the currently advanced natural language processing (NLP) tasks such as textual classification, neural machine translation (NMT), abstractive summarization and question-answering (QA). However, the robustness…

Computation and Language · Computer Science 2024-11-14 Jiyao Li , Mingze Ni , Yongshun Gong , Wei Liu

Recent work has highlighted the vulnerability of many deep machine learning models to adversarial examples. It attracts increasing attention to adversarial attacks, which can be used to evaluate the security and robustness of models before…

Machine Learning · Computer Science 2020-06-22 Xuli Sun , Shiliang Sun

Artificial Intelligence (AI) relies heavily on deep learning - a technology that is becoming increasingly popular in real-life applications of AI, even in the safety-critical and high-risk domains. However, it is recently discovered that…

Cryptography and Security · Computer Science 2022-02-16 Jie Wang , Ghulam Mubashar Hassan , Naveed Akhtar

We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with a Trojan trigger. Our approach is based on a novel…

Machine Learning · Computer Science 2020-12-07 Karan Sikka , Indranil Sur , Susmit Jha , Anirban Roy , Ajay Divakaran

Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data. The backdoor can be activated when a normal input is stamped with a…

Machine Learning · Computer Science 2021-01-05 Siyuan Cheng , Yingqi Liu , Shiqing Ma , Xiangyu Zhang

Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…

Machine Learning · Computer Science 2022-05-20 Thomas Cilloni , Charles Walter , Charles Fleming