English
Related papers

Related papers: Layer-Wise Perturbations via Sparse Autoencoders f…

200 papers

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Machine Learning · Computer Science 2025-08-07 Gonçalo Paulo , Alex Mallen , Caden Juang , Nora Belrose

Deep neural networks can be vulnerable to adversarially crafted examples, presenting significant risks to practical applications. A prevalent approach for adversarial attacks relies on the transferability of adversarial examples, which are…

Information Retrieval · Computer Science 2024-11-12 Shanjun Xu , Linghui Li , Kaiguo Yuan , Bingyu Li

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

Although federated learning improves privacy of training data by exchanging local gradients or parameters rather than raw data, the adversary still can leverage local gradients and parameters to obtain local training data by launching…

Machine Learning · Computer Science 2021-08-17 Xue Yang , Yan Feng , Weijun Fang , Jun Shao , Xiaohu Tang , Shu-Tao Xia , Rongxing Lu

This article proposes Adversarially-Trained Normalized Noisy-Feature Auto-Encoder (ATNNFAE) for byte-level text generation. An ATNNFAE consists of an auto-encoder where the internal code is normalized on the unit sphere and corrupted by…

Computation and Language · Computer Science 2018-11-13 Xiang Zhang , Yann LeCun

The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated text detectors have been proposed to mitigate these risks,…

Computation and Language · Computer Science 2025-10-31 Yize Cheng , Vinu Sankar Sadasivan , Mehrdad Saberi , Shoumik Saha , Soheil Feizi

Text generation with generative adversarial networks (GANs) can be divided into the text-based and code-based categories according to the type of signals used for discrimination. In this work, we introduce a novel text-based approach called…

Computation and Language · Computer Science 2019-04-24 Md. Akmal Haidar , Mehdi Rezagholizadeh , Alan Do-Omri , Ahmad Rashid

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating human-like text, but their output may not be aligned with the user or even produce harmful content. This paper presents a novel approach to detect and…

Computation and Language · Computer Science 2024-12-06 Ruben Härle , Felix Friedrich , Manuel Brack , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Machine Learning · Computer Science 2019-10-04 He Zhao , Trung Le , Paul Montague , Olivier De Vel , Tamas Abraham , Dinh Phung

The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural…

Computation and Language · Computer Science 2020-06-15 Zhaoyang Wang , Hongtao Wang

This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor…

Human-Computer Interaction · Computer Science 2020-12-21 Brandon Laughlin , Christopher Collins , Karthik Sankaranarayanan , Khalil El-Khatib

Security-sensitive applications that rely on Deep Neural Networks (DNNs) are vulnerable to small perturbations that are crafted to generate Adversarial Examples(AEs). The AEs are imperceptible to humans and cause DNN to misclassify them.…

Cryptography and Security · Computer Science 2021-06-22 Ahmed Aldahdooh , Wassim Hamidouche , Olivier Déforges

Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to…

Computer Vision and Pattern Recognition · Computer Science 2017-12-07 Weilin Xu , David Evans , Yanjun Qi

Semi-supervised semantic segmentation allows model to mine effective supervision from unlabeled data to complement label-guided training. Recent research has primarily focused on consistency regularization techniques, exploring…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Xiaoyang Wang , Huihui Bai , Limin Yu , Yao Zhao , Jimin Xiao

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Gaozheng Pei , Ke Ma , Dongpeng Zhang , Chengzhi Sun , Qianqian Xu , Qingming Huang

Non-negative matrix factorization (NMF) is a common method for generating topic models from text data. NMF is widely accepted for producing good results despite its relative simplicity of implementation and ease of computation. One…

Machine Learning · Computer Science 2016-08-09 Brendan Gavin , Vijay Gadepally , Jeremy Kepner

Large language models (LLMs) have exhibited outstanding performance in natural language processing tasks. However, these models remain susceptible to adversarial attacks in which slight input perturbations can lead to harmful or misleading…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Minkyoung Kim , Yunha Kim , Hyeram Seo , Heejung Choi , Jiye Han , Gaeun Kee , Soyoung Ko , HyoJe Jung , Byeolhee Kim , Young-Hak Kim , Sanghyun Park , Tae Joon Jun

Adversarial patch is an important form of real-world adversarial attack that brings serious risks to the robustness of deep neural networks. Previous methods generate adversarial patches by either optimizing their perturbation values while…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Xingxing Wei , Ying Guo , Jie Yu , Bo Zhang

Recently, some research show that deep neural networks are vulnerable to the adversarial attacks, the well-trainned samples or patches could be used to trick the neural network detector or human visual perception. However, these adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-12-29 Xianyi Chen , Fazhan Liu , Dong Jiang , Kai Yan

In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges. This paper introduces an innovative…

Computer Vision and Pattern Recognition · Computer Science 2024-01-22 YuTeng Ye , Jiale Cai , Hang Zhou , Guanwen Li , Youjia Zhang , Zikai Song , Chenxing Gao , Junqing Yu , Wei Yang
‹ Prev 1 4 5 6 7 8 10 Next ›