English
Related papers

Related papers: Towards Robust Toxic Content Classification

200 papers

Large Language Models have demonstrated impressive fluency across diverse tasks, yet their tendency to produce toxic content remains a critical challenge for AI safety and public trust. Existing toxicity mitigation approaches primarily…

Computation and Language · Computer Science 2025-09-23 Zuhair Hasan Shaik , Abdullah Mazhar , Aseem Srivastava , Md Shad Akhtar

Adversarial attacks are often considered as threats to the robustness of Deep Neural Networks (DNNs). Various defending techniques have been developed to mitigate the potential negative impact of adversarial attacks against task…

Machine Learning · Computer Science 2022-04-12 Jianzhang Zheng , Fan Yang , Hao Shen , Xuan Tang , Mingsong Chen , Liang Song , Xian Wei

What should a malicious user write next to fool a detection model? Identifying malicious users is critical to ensure the safety and integrity of internet platforms. Several deep learning-based detection models have been created. However,…

Machine Learning · Computer Science 2021-10-20 Bing He , Mustaque Ahamad , Srijan Kumar

Deep Neural Networks (DNNs) are known to be vulnerable to the maliciously generated adversarial examples. To detect these adversarial examples, previous methods use artificially designed metrics to characterize the properties of…

Computer Vision and Pattern Recognition · Computer Science 2019-11-18 Xiaofeng Mao , Yuefeng Chen , Yuhong Li , Yuan He , Hui Xue

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ruidong Chen , Honglin Guo , Lanjun Wang , Chenyu Zhang , Weizhi Nie , An-An Liu

Deep learning (DL) models for natural language-to-code generation have become integral to modern software development pipelines. However, their heavy reliance on large amounts of data, often collected from unsanitized online sources,…

Cryptography and Security · Computer Science 2025-09-01 Cristina Improta

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Cryptography and Security · Computer Science 2025-12-05 Bingyin Zhao , Yingjie Lao

Machine learning models provide statistically impressive results which might be individually unreliable. To provide reliability, we propose an Epistemic Classifier (EC) that can provide justification of its belief using support from the…

Machine Learning · Computer Science 2020-10-20 Chitresh Bhushan , Zhaoyuan Yang , Nurali Virani , Naresh Iyer

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

Named entity recognition (NER) models often struggle with noisy inputs, such as those with spelling mistakes or errors generated by Optical Character Recognition processes, and learning a robust NER model is challenging. Existing robust NER…

Computation and Language · Computer Science 2024-07-29 Chaoyi Ai , Yong Jiang , Shen Huang , Pengjun Xie , Kewei Tu

We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to…

Cryptography and Security · Computer Science 2025-06-03 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but their robustness against tokenizer poisoning remains underexplored. In this work, we assess the vulnerability of dense retrieval systems…

Computation and Language · Computer Science 2024-10-29 Ming Zhong , Zhizhi Wu , Nanako Honda

Research on adversarial attacks are becoming widely popular in the recent years. One of the unexplored areas where prior research is lacking is the effect of adversarial attacks on code-mixed data. Therefore, in the present work, we have…

Computation and Language · Computer Science 2021-11-02 Sourya Dipta Das , Ayan Basak , Soumil Mandal , Dipankar Das

Large Language Models (LLMs) trained on web-scale corpora inherently absorb toxic patterns from their training data. This leads to toxic degeneration where even innocuous prompts can trigger harmful outputs. This phenomenon poses…

Computation and Language · Computer Science 2026-05-18 Mokshit Surana , Archit Rathod , Akshaj Satishkumar

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Machine Learning · Computer Science 2022-02-03 Michael Everett , Bjorn Lutjens , Jonathan P. How

In this paper we provide an approach for deep learning that protects against adversarial examples in image classification-type networks. The approach relies on two mechanisms:1) a mechanism that increases robustness at the expense of…

Machine Learning · Computer Science 2021-01-07 Yuting Liang , Reza Samavi

Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper, we propose a novel adversarial detector, which consists of a…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Takayuki Osakabe , Maungmaung Aprilpyone , Sayaka Shiota , Hitoshi Kiya

Machine learning based language models have recently made significant progress, which introduces a danger to spread misinformation. To combat this potential danger, several methods have been proposed for detecting text written by these…

Cryptography and Security · Computer Science 2022-01-20 Max Wolff , Stuart Wolff

Deep learning classifiers are prone to latching onto dominant confounders present in a dataset rather than on the causal markers associated with the target class, leading to poor generalization and biased predictions. Although…

Computer Vision and Pattern Recognition · Computer Science 2024-05-16 Nima Fathi , Amar Kumar , Brennan Nichyporuk , Mohammad Havaei , Tal Arbel

Intelligent machine learning approaches are finding active use for event detection and identification that allow real-time situational awareness. Yet, such machine learning algorithms have been shown to be susceptible to adversarial attacks…

Systems and Control · Electrical Eng. & Systems 2024-04-23 Obai Bahwal , Oliver Kosut , Lalitha Sankar