English
Related papers

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

200 papers

Large Language Models frequently generate fluent but factually incorrect text. We propose Adaptive Activation Cancellation (AAC), a real-time inference-time framework that treats hallucination-associated neural activations as structured…

Computation and Language · Computer Science 2026-03-12 Eric Yocam , Varghese Vaidyan , Gurcan Comert , Paris Kalathas , Yong Wang , Judith L. Mwakalonge

Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose high-level representation guided denoiser (HGD) as a defense for image classification. Standard…

Computer Vision and Pattern Recognition · Computer Science 2018-05-09 Fangzhou Liao , Ming Liang , Yinpeng Dong , Tianyu Pang , Xiaolin Hu , Jun Zhu

In recent years, large language models (LLMs) have made remarkable advancements, yet hallucination, where models produce inaccurate or non-factual statements, remains a significant challenge for real-world deployment. Although current…

Computation and Language · Computer Science 2025-06-03 Qing Li , Jiahui Geng , Zongxiong Chen , Derui Zhu , Yuxia Wang , Congbo Ma , Chenyang Lyu , Fakhri Karray

As the deployment of NLP systems in critical applications grows, ensuring the robustness of large language models (LLMs) against adversarial attacks becomes increasingly important. Large language models excel in various NLP tasks but remain…

Computation and Language · Computer Science 2024-05-03 Zhenning Yang , Ryan Krawec , Liang-Yuan Wu

Large language models (LLMs) exhibit hallucinations in long-form question-answering tasks across various domains and wide applications. Current hallucination detection and mitigation datasets are limited in domains and sizes, which struggle…

Computation and Language · Computer Science 2024-12-20 Yuzhe Gu , Ziwei Ji , Wenwei Zhang , Chengqi Lyu , Dahua Lin , Kai Chen

Although Large Audio-Language Models (LALMs) deliver state-of-the-art (SOTA) performance, they frequently suffer from hallucinations, e.g. generating text not grounded in the audio input. We analyze these grounding failures and identify a…

Large language models(LLMs) excel at text generation and knowledge question-answering tasks, but they are prone to generating hallucinated content, severely limiting their application in high-risk domains. Current hallucination detection…

Computation and Language · Computer Science 2025-12-25 Shize Liang , Hongzhi Wang

Large Audio-Language Models (LALMs) can take audio and text as the inputs and answer questions about the audio. While prior LALMs have shown strong performance on standard benchmarks, there has been alarming evidence that LALMs can…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-16 Tzu-wen Hsu , Ke-Han Lu , Cheng-Han Chiang , Hung-yi Lee

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Computation and Language · Computer Science 2025-10-08 Harethah Abu Shairah , Hasan Abed Al Kader Hammoud , Bernard Ghanem , George Turkiyyah

Large Vision-Language Models (LVLMs) have advanced multimodal understanding, yet their reliability is limited by hallucination, where generated content conflicts with visual facts. Existing mitigation methods either rely on costly external…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Ruoxi Cheng , Haoxuan Ma , Zhengfei Hai , Yiyan Huang , Ranjie Duan , Tianle Zhang , Xu Yang , Ziyi Ye , Xingjun Ma

Reducing the `$\textit{hallucination}$' problem of Large Language Models (LLMs) is crucial for their wide applications. A comprehensive and fine-grained measurement of the hallucination is the first key step for the governance of this issue…

Computation and Language · Computer Science 2024-05-31 Ziwei Ji , Yuzhe Gu , Wenwei Zhang , Chengqi Lyu , Dahua Lin , Kai Chen

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Computation and Language · Computer Science 2025-05-20 Zhenhao Li , Huichi Zhou , Marek Rei , Lucia Specia

Visual hallucinations in Large Language Models (LLMs), where the model generates responses that are inconsistent with the visual input, pose a significant challenge to their reliability, particularly in contexts where precise and…

Computer Vision and Pattern Recognition · Computer Science 2025-06-30 Nokimul Hasan Arif , Shadman Rabby , Md Hefzul Hossain Papon , Sabbir Ahmed

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

Computation and Language · Computer Science 2025-12-02 Jakub Hoscilowicz , Artur Janicki

Recent studies have shown that large vision-language models (LVLMs) often suffer from the issue of object hallucinations (OH). To mitigate this issue, we introduce an efficient method that edits the model weights based on an unsafe…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Le Yang , Ziwei Zheng , Boxu Chen , Zhengyu Zhao , Chenhao Lin , Chao Shen

Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…

Computation and Language · Computer Science 2024-06-11 Duy C. Hoang , Quang H. Nguyen , Saurav Manchanda , MinLong Peng , Kok-Seng Wong , Khoa D. Doan

Active Noise Cancellation (ANC) algorithms aim to suppress unwanted acoustic disturbances by generating anti-noise signals that destructively interfere with the original noise in real time. Although recent deep learning-based ANC algorithms…

Information Theory · Computer Science 2025-05-26 François Derrida , Shahar Lutati , Eliya Nachmani

Large Audio Language Models (LALMs) achieve strong performance on audio-language tasks; however, their reliability in real-world settings remains underexplored. We introduce Audio Hallucination Attacks (AHA), an attack suite called…

Multimodal large language models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet they remain highly susceptible to hallucinations, producing content that is fluent but inconsistent with visual evidence.…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Youxu Shi , Suorong Yang , Dong Liu
‹ Prev 1 2 3 10 Next ›