English
Related papers

Related papers: Towards Building a Robust Toxicity Predictor

200 papers

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Computation and Language · Computer Science 2024-01-17 Tom Roth , Inigo Jauregi Unanue , Alsharif Abuadbba , Massimo Piccardi

This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a 'backdoor poisoning' attack on NLP models. Our poisoning attack utilizes conditional…

Computation and Language · Computer Science 2020-10-07 Alvin Chan , Yi Tay , Yew-Soon Ong , Aston Zhang

Safety classifiers are critical in mitigating toxicity on online forums such as social media and in chatbots. Still, they continue to be vulnerable to emergent, and often innumerable, adversarial attacks. Traditional automated adversarial…

Computation and Language · Computer Science 2024-06-26 Yash Kumar Lal , Preethi Lahoti , Aradhana Sinha , Yao Qin , Ananth Balashankar

Adversarial attacks are a major challenge faced by current machine learning research. These purposely crafted inputs fool even the most advanced models, precluding their deployment in safety-critical applications. Extensive research in…

Artificial Intelligence · Computer Science 2023-06-30 Edoardo Mosca , Shreyash Agarwal , Javier Rando , Georg Groh

Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts have sought to identify which source samples are the most…

Computation and Language · Computer Science 2023-06-26 Vyas Raina , Mark Gales

Lack of moderation in online communities enables participants to incur in personal aggression, harassment or cyberbullying, issues that have been accentuated by extremist radicalisation in the contemporary post-truth politics scenario. This…

Computation and Language · Computer Science 2018-01-08 Nestor Rodriguez , Sergio Rojas-Galeano

Test-time adaptation (TTA) updates the model weights during the inference stage using testing data to enhance generalization. However, this practice exposes TTA to adversarial risks. Existing studies have shown that when TTA is updated with…

Machine Learning · Computer Science 2025-03-03 Yongyi Su , Yushu Li , Nanqing Liu , Kui Jia , Xulei Yang , Chuan-Sheng Foo , Xun Xu

In malware behavioral analysis, the list of accessed and created files very often indicates whether the examined file is malicious or benign. However, malware authors are trying to avoid detection by generating random filenames and/or…

Machine Learning · Computer Science 2021-10-26 Marek Galovic , Branislav Bosansky , Viliam Lisy

Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a representative estimate of…

Machine Learning · Computer Science 2026-01-27 Giulio Rossolini

The open-endedness of large language models (LLMs) combined with their impressive capabilities may lead to new safety issues when being exploited for malicious use. While recent studies primarily focus on probing toxic outputs that can be…

Computation and Language · Computer Science 2023-11-30 Jiaxin Wen , Pei Ke , Hao Sun , Zhexin Zhang , Chengfei Li , Jinfeng Bai , Minlie Huang

Language Models today provide a high accuracy across a large number of downstream tasks. However, they remain susceptible to adversarial attacks, particularly against those where the adversarial examples maintain considerable similarity to…

Computation and Language · Computer Science 2023-07-25 Neel Bhandari , Pin-Yu Chen

Building an effective adversarial attacker and elaborating on countermeasures for adversarial attacks for natural language processing (NLP) have attracted a lot of research in recent years. However, most of the existing approaches focus on…

Computation and Language · Computer Science 2020-10-20 Wenjuan Han , Liwen Zhang , Yong Jiang , Kewei Tu

Machine learning algorithms are often vulnerable to adversarial examples that have imperceptible alterations from the original counterparts but can fool the state-of-the-art models. It is helpful to evaluate or even improve the robustness…

Computation and Language · Computer Science 2020-04-10 Di Jin , Zhijing Jin , Joey Tianyi Zhou , Peter Szolovits

Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…

Machine Learning · Computer Science 2022-03-09 Maria-Florina Balcan , Avrim Blum , Steve Hanneke , Dravyansh Sharma

Large language models (LLMs) can often be made to behave in undesirable ways that they are explicitly fine-tuned not to. For example, the LLM red-teaming literature has produced a wide variety of 'jailbreaking' techniques to elicit harmful…

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial examples. There is a need to build defenses that protect…

Machine Learning · Computer Science 2020-08-20 Alfred Laugros , Alice Caplier , Matthieu Ospici

We introduce the Text Classification Attack Benchmark (TCAB), a dataset for analyzing, understanding, detecting, and labeling adversarial attacks against text classifiers. TCAB includes 1.5 million attack instances, generated by twelve…

Machine Learning · Computer Science 2022-10-25 Kalyani Asthana , Zhouhang Xie , Wencong You , Adam Noack , Jonathan Brophy , Sameer Singh , Daniel Lowd

Understanding the reliability of natural language generation is critical for deploying foundation models in security-sensitive domains. While certified poisoning defenses provide provable robustness bounds for classification tasks, they are…

Machine Learning · Computer Science 2026-02-11 Mihnea Ghitu , Matthew Wicker

Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, detection-based defense, aims to distinguish adversarial…

Computation and Language · Computer Science 2023-02-07 Lingfeng Shen , Ze Zhang , Haiyun Jiang , Ying Chen

Deep neural networks (DNNs) have achieved remarkable success in various tasks (e.g., image classification, speech recognition, and natural language processing (NLP)). However, researchers have demonstrated that DNN-based models are…

Computation and Language · Computer Science 2021-04-22 Wenqi Wang , Run Wang , Lina Wang , Zhibo Wang , Aoshuang Ye