English
Related papers

Related papers: Adv-OLM: Generating Textual Adversaries via OLM

200 papers

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Han Liu , Jiaqi Li , Zhi Xu , Xiaotong Zhang , Xiaoming Xu , Fenglong Ma , Yuanman Li , Hong Yu

Despite the impressive adaptability of large language models (LLMs), challenges remain in ensuring their security, transparency, and interpretability. Given their susceptibility to adversarial attacks, LLMs need to be defended with an…

Artificial Intelligence · Computer Science 2024-10-11 Tomas Bueno Momcilovic , Beat Buesser , Giulio Zizzo , Mark Purcell , Dian Balta

Deep neural networks are vulnerable to adversarial examples, which poses security concerns on these algorithms due to the potentially severe consequences. Adversarial attacks serve as an important surrogate to evaluate the robustness of…

Machine Learning · Computer Science 2018-03-23 Yinpeng Dong , Fangzhou Liao , Tianyu Pang , Hang Su , Jun Zhu , Xiaolin Hu , Jianguo Li

Large Language Models (LLMs) are swiftly advancing in architecture and capability, and as they integrate more deeply into complex systems, the urgency to scrutinize their security properties grows. This paper surveys research in the…

Computation and Language · Computer Science 2023-10-18 Erfan Shayegani , Md Abdullah Al Mamun , Yu Fu , Pedram Zaree , Yue Dong , Nael Abu-Ghazaleh

Machine learning models using transaction records as inputs are popular among financial institutions. The most efficient models use deep-learning architectures similar to those in the NLP community, posing a challenge due to their…

Large language models (LLMs) have exhibited remarkable fluency across various tasks. However, their unethical applications, such as disseminating disinformation, have become a growing concern. Although recent works have proposed a number of…

Computation and Language · Computer Science 2024-10-07 James Wang , Ran Li , Junfeng Yang , Chengzhi Mao

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…

Computation and Language · Computer Science 2024-01-11 Hai Zhu , Zhaoqing Yang , Weiwei Shang , Yuren Wu

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust…

Computer Vision and Pattern Recognition · Computer Science 2018-08-07 Vivek B. S. , Konda Reddy Mopuri , R. Venkatesh Babu

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

Traffic state prediction is necessary for many Intelligent Transportation Systems applications. Recent developments of the topic have focused on network-wide, multi-step prediction, where state of the art performance is achieved via deep…

Machine Learning · Computer Science 2024-03-12 Bibek Poudel , Weizi Li

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

Cryptography and Security · Computer Science 2016-05-25 Nicolas Papernot , Patrick McDaniel , Ian Goodfellow

Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from the underlying manifold of normal texts, whereas pre-trained…

Computation and Language · Computer Science 2025-04-15 Xiaomei Zhang , Zhaoxi Zhang , Yanjun Zhang , Xufei Zheng , Leo Yu Zhang , Shengshan Hu , Shirui Pan

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but refuse to answer requests that could cause harm. However,…

We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified…

Machine Learning · Computer Science 2021-03-23 Ying Xu , Xu Zhong , Antonio Jimeno Yepes , Jey Han Lau

We present a method for adversarial input generation against black box models for reading comprehension based question answering. Our approach is composed of two steps. First, we approximate a victim black box model via model extraction…

Machine Learning · Computer Science 2020-11-03 Naveen Jafer Nizar , Ari Kobren

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation. As the practical applications of vision-language models become…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Peng Xie , Yequan Bie , Jianda Mao , Yangqiu Song , Yang Wang , Hao Chen , Kani Chen

Eliciting harmful behavior from large language models (LLMs) is an important task to ensure the proper alignment and safety of the models. Often when training LLMs, ethical guidelines are followed yet alignment failures may still be…

Cryptography and Security · Computer Science 2024-08-20 Robert J. Moss

In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies have shown that PLMs are vulnerable to attacks from…

Computation and Language · Computer Science 2024-02-06 Shuguang Chen , Leonardo Neves , Thamar Solorio

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different…

Cryptography and Security · Computer Science 2019-02-15 Chaowei Xiao , Bo Li , Jun-Yan Zhu , Warren He , Mingyan Liu , Dawn Song