English
Related papers

Related papers: Reproducing HotFlip for Corpus Poisoning Attacks i…

200 papers

Retrieval-augmented generation (RAG) systems enhance large language models by incorporating external knowledge, addressing issues like outdated internal knowledge and hallucination. However, their reliance on external knowledge bases makes…

Machine Learning · Computer Science 2025-03-28 Cheng Wang , Yiwei Wang , Yujun Cai , Bryan Hooi

To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between the…

Computation and Language · Computer Science 2022-04-13 Jiawei Zhou , Xiaoguang Li , Lifeng Shang , Lan Luo , Ke Zhan , Enrui Hu , Xinyu Zhang , Hao Jiang , Zhao Cao , Fan Yu , Xin Jiang , Qun Liu , Lei Chen

There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting. These methods attack natural language classifiers by perturbing certain important words until the classifier…

Machine Learning · Computer Science 2021-05-04 Mahmoud Hossam , Trung Le , He Zhao , Viet Huynh , Dinh Phung

While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Yuwei Niu , Shuo He , Qi Wei , Zongyu Wu , Feng Liu , Lei Feng

Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model.…

Computation and Language · Computer Science 2020-09-22 Yuan Zang , Bairu Hou , Fanchao Qi , Zhiyuan Liu , Xiaojun Meng , Maosong Sun

Most current classifiers are vulnerable to adversarial examples, small input perturbations that change the classification output. Many existing attack algorithms cover various settings, from white-box to black-box classifiers, but typically…

Machine Learning · Computer Science 2021-06-15 Carl-Johann Simon-Gabriel , Noman Ahmed Sheikh , Andreas Krause

Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous approaches have…

Artificial Intelligence · Computer Science 2023-10-12 Luiza Pozzobon , Beyza Ermis , Patrick Lewis , Sara Hooker

In this paper, we present a novel algorithm, FastWordBug, to efficiently generate small text perturbations in a black-box setting that forces a sentiment analysis or text classification mode to make an incorrect prediction. By combining the…

Computation and Language · Computer Science 2020-02-04 Dou Goodman , Lv Zhonghou , Wang minghua

Transformer-based models have advanced the field of question answering, but multi-hop reasoning, where answers require combining evidence across multiple passages, remains difficult. This paper presents a comprehensive evaluation of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Zichen Zhang , Kunlong Zhang , Hongwei Ruan , Yiming Luo

Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations that mislead deep learning models. While adversarial example detection offers a lightweight…

Computation and Language · Computer Science 2026-03-16 He Zhu , Yanshu Li , Wen Liu , Haitian Yang

Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions.…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Raz Lapid , Moshe Sipper

Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming…

Machine Learning · Computer Science 2019-04-05 Yotam Gil , Yoav Chai , Or Gorodissky , Jonathan Berant

With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing…

Information Retrieval · Computer Science 2026-02-13 Hongyue Zhang , Mingming Li , Dongqin Liu , Hui Wang , Yaning Zhang , Xi Zhou , Honglei Lv , Jiao Dai , Jizhong Han

Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigger-less attack, the attacker can modify the training set but…

Machine Learning · Computer Science 2022-10-18 Yuhao Zhang , Aws Albarghouthi , Loris D'Antoni

Retrieval-Augmented Generation (RAG) systems enhance response credibility and traceability by displaying reference contexts, but this transparency simultaneously introduces a novel black-box attack vector. Existing document poisoning…

Computation and Language · Computer Science 2026-01-27 Runqi Sui

LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses.…

Machine Learning · Computer Science 2025-11-07 Advik Raj Basani , Xiao Zhang

Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small…

Cryptography and Security · Computer Science 2025-12-03 Issa Oe , Keiichiro Yamamura , Hiroki Ishikura , Ryo Hamahira , Katsuki Fujisawa

Multimodal contrastive learning methods like CLIP train on noisy and uncurated training datasets. This is cheaper than labeling datasets manually, and even improves out-of-distribution robustness. We show that this practice makes backdoor…

Machine Learning · Computer Science 2022-03-29 Nicholas Carlini , Andreas Terzis

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the…

Computation and Language · Computer Science 2024-12-10 Jonathan Hayase , Ema Borevkovic , Nicholas Carlini , Florian Tramèr , Milad Nasr

With proliferation of user generated contents in social media platforms, establishing mechanisms to automatically identify toxic and abusive content becomes a prime concern for regulators, researchers, and society. Keeping the balance…

Computation and Language · Computer Science 2021-06-10 Djamila Romaissa Beddiar , Md Saroar Jahan , Mourad Oussalah