English
Related papers

Related papers: H-Node Attack and Defense in Large Language Models

200 papers

Hallucinations in deployed language models can have real consequences for downstream decisions in domains such as healthcare, legal, and financial services. In production, detection has to run on what the deployed system can see: the query,…

Artificial Intelligence · Computer Science 2026-05-11 Javier Marín

Large Vision-Language Models (LVLMs) are an extension of Large Language Models (LLMs) that facilitate processing both image and text inputs, expanding AI capabilities. However, LVLMs struggle with object hallucinations due to their reliance…

Computation and Language · Computer Science 2024-08-12 Avshalom Manevich , Reut Tsarfaty

In recent times, deep neural networks (DNNs) have been successfully adopted for various applications. Despite their notable achievements, it has become evident that DNNs are vulnerable to sophisticated adversarial attacks, restricting their…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Alik Pramanick , Mayank Bansal , Utkarsh Srivastava , Suklav Ghosh , Arijit Sur

Deep neural networks (DNNs) are notoriously vulnerable to adversarial attacks that place carefully crafted perturbations on normal examples to fool DNNs. To better understand such attacks, a characterization of the features carried by…

Machine Learning · Computer Science 2024-03-26 Rui Zheng , Yuhao Zhou , Zhiheng Xi , Tao Gui , Qi Zhang , Xuanjing Huang

Over the past two years, the use of large language models (LLMs) has advanced rapidly. While these LLMs offer considerable convenience, they also raise security concerns, as LLMs are vulnerable to adversarial attacks by some well-designed…

Computation and Language · Computer Science 2025-04-24 Guang Lin , Toshihisa Tanaka , Qibin Zhao

Large Language Models (LLMs) remain vulnerable to multi-turn jailbreak attacks. We introduce HarmNet, a modular framework comprising ThoughtNet, a hierarchical semantic network; a feedback-driven Simulator for iterative query refinement;…

Cryptography and Security · Computer Science 2025-10-22 Sidhant Narula , Javad Rafiei Asl , Mohammad Ghasemigol , Eduardo Blanco , Daniel Takabi

Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG. We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the…

Computation and Language · Computer Science 2026-02-03 Zehua Cheng , Jianwei Yang , Wei Dai , Jiahao Sun

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Shangbo Wu , Yu-an Tan , Yajie Wang , Ruinan Ma , Wencong Ma , Yuanzhang Li

We introduce a proxy-analyzer framework for detecting hallucinations in large language models. Instead of looking inside the generating model, our system reads already-generated text through a small locally hosted open-weight model and…

Computation and Language · Computer Science 2026-05-11 Akshita Singh , Prabesh Paudel , Siddhartha Roy

Motivated by the general robustness properties of the 01 loss we propose a single hidden layer 01 loss neural network trained with stochastic coordinate descent as a defense against adversarial attacks in machine learning. One measure of a…

Machine Learning · Computer Science 2020-08-24 Yunzhe Xue , Meiyan Xie , Usman Roshan

Large Language Models (LLMs) often hallucinate, generating nonsensical or false information that can be especially harmful in sensitive fields such as medicine or law. To study this phenomenon systematically, we introduce FalseCite, a…

Computation and Language · Computer Science 2026-02-13 Nathan Mao , Varun Kaushik , Shreya Shivkumar , Parham Sharafoleslami , Kevin Zhu , Sunishchal Dev

Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, comparing two learned…

Computer Vision and Pattern Recognition · Computer Science 2025-04-17 Samuel Räber , Andreas Plesner , Till Aczel , Roger Wattenhofer

The vulnerability of Convolutional Neural Networks (CNNs) to adversarial samples has recently garnered significant attention in the machine learning community. Furthermore, recent studies have unveiled the existence of universal adversarial…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Juanjuan Weng , Zhiming Luo , Dazhen Lin , Shaozi Li

To develop trustworthy Vision-Language Models (VLMs), it is essential to address adversarial robustness and hallucination mitigation, both of which impact factual accuracy in high-stakes applications such as defense and healthcare. Existing…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Chung-En , Yu , Hsuan-Chih , Chen , Brian Jalaian , Nathaniel D. Bastian

Multi-modal large language models (MLLMs) have been shown to efficiently integrate natural language with visual information to handle multi-modal tasks. However, MLLMs still face a fundamental limitation of hallucinations, where they tend…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Chaoya Jiang , Haiyang Xu , Mengfan Dong , Jiaxing Chen , Wei Ye , Ming Yan , Qinghao Ye , Ji Zhang , Fei Huang , Shikun Zhang

Deep learning-based object detection models play a critical role in real-world applications such as autonomous driving and security surveillance systems, yet they remain vulnerable to adversarial examples. In this work, we propose an…

Cryptography and Security · Computer Science 2025-12-19 Min Geun Song , Gang Min Kim , Woonmin Kim , Yongsik Kim , Jeonghyun Sim , Sangbeom Park , Huy Kang Kim

Recent work has shown that language models' refusal behavior is primarily encoded in a single direction in their latent space, making it vulnerable to targeted attacks. Although Latent Adversarial Training (LAT) attempts to improve…

Computation and Language · Computer Science 2025-04-29 Alexandra Abbas , Nora Petrova , Helios Ael Lyons , Natalia Perez-Campanero

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing…

Computation and Language · Computer Science 2026-02-02 Omar Mahmoud , Ali Khalil , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address…

Artificial Intelligence · Computer Science 2026-02-06 Kim Hammar , Tansu Alpcan , Emil Lupu

Hallucinations remain a significant challenge in current Generative AI models, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized Artificial Intelligent Agents can help…

Computation and Language · Computer Science 2025-01-27 Diego Gosmar , Deborah A. Dahl
‹ Prev 1 4 5 6 7 8 10 Next ›