English
Related papers

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

200 papers

Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade model performance. Conventional defense mechanisms…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Eylon Mizrahi , Raz Lapid , Moshe Sipper

Large Language Models have demonstrated remarkable capabilities across diverse tasks, yet they frequently generate hallucinations outputs that are fluent but factually incorrect or unsupported. We propose Counterfactual Probing, a novel…

Computation and Language · Computer Science 2025-08-05 Yijun Feng

Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…

Machine Learning · Computer Science 2019-11-25 Sambuddha Saha , Aashish Kumar , Pratyush Sahay , George Jose , Srinivas Kruthiventi , Harikrishna Muralidhara

Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the…

Machine Learning · Computer Science 2018-03-26 Rajeev Ranjan , Swami Sankaranarayanan , Carlos D. Castillo , Rama Chellappa

Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Tao Bai , Jun Zhao , Lanqing Guo , Bihan Wen

This paper proposes a deep cerebellar model articulation controller (DCMAC) for adaptive noise cancellation (ANC). We expand upon the conventional CMAC by stacking sin-gle-layer CMAC models into multiple layers to form a DCMAC model and…

Systems and Control · Computer Science 2017-05-03 Yu Tsao , Hao-Chun Chu , Shih-Wei Lan , Shih-Hau Fang , Junghsi Lee , Chih-Min Lin

While Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive paradigm comparable to autoregressive (AR) models, their faithfulness, specifically regarding hallucination, remains largely underexplored. To…

Computation and Language · Computer Science 2026-04-14 Zhengnan Guo , Fei Tan

Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs. However, these models often hallucinate non-existent sound events, reducing their reliability in real-world applications.…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-02 Chun-Yi Kuan , Hung-yi Lee

Jailbreak attacks pose persistent threats to large language models (LLMs). Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and…

Cryptography and Security · Computer Science 2025-09-19 Yuanbo Xie , Yingjie Zhang , Tianyun Liu , Duohe Ma , Tingwen Liu

With the growing adoption of Large Language Models (LLMs) in critical areas, ensuring their security against jailbreaking attacks is paramount. While traditional defenses primarily rely on refusing malicious prompts, recent logit-level…

Cryptography and Security · Computer Science 2025-07-31 Yassine Rachidy , Jihad Rbaiti , Youssef Hmamouche , Faissal Sehbaoui , Amal El Fallah Seghrouchni

Object hallucination in Large Vision-Language Models (LVLMs) significantly hinders their reliable deployment. Existing methods struggle to balance efficiency and accuracy: they often require expensive reference models and multiple forward…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Yangguang Lin , Quan Fang , Yufei Li , Jiachen Sun , Junyu Gao , Jitao Sang

Contextual hallucinations -- statements unsupported by given context -- remain a significant challenge in AI. We demonstrate a practical interpretability insight: a generator-agnostic observer model detects hallucinations via a single…

Machine Learning · Computer Science 2025-08-01 Charles O'Neill , Slava Chalnev , Chi Chi Zhao , Max Kirkby , Mudith Jayasekara

Hallucination, or the generation of incorrect or fabricated information, remains a critical challenge in large language models (LLMs), particularly in high-stake domains such as legal question answering (QA). In order to mitigate the…

Computation and Language · Computer Science 2025-01-14 Yinghao Hu , Leilei Gan , Wenyi Xiao , Kun Kuang , Fei Wu

Multi-component natural language processing (NLP) pipelines are increasingly deployed for high-stakes decisions, yet no existing adversarial method can test their robustness under realistic conditions: binary-only feedback, no gradient…

Artificial Intelligence · Computer Science 2026-04-28 Mazal Bethany , Kim-Kwang Raymond Choo , Nishant Vishwamitra , Peyman Najafirad

Large language models (LLMs) are vulnerable to adversarial attacks that can elicit harmful responses. Defending against such attacks remains challenging due to the opacity of jailbreaking mechanisms and the high computational cost of…

Machine Learning · Computer Science 2025-03-21 Lei Yu , Virginie Do , Karen Hambardzumyan , Nicola Cancedda

Despite remarkable advancements in mitigating hallucinations in large language models (LLMs) by retrieval augmentation, it remains challenging to measure the reliability of LLMs using static question-answering (QA) data. Specifically, given…

Computation and Language · Computer Science 2024-06-04 Xiaodong Yu , Hao Cheng , Xiaodong Liu , Dan Roth , Jianfeng Gao

Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image.…

Machine Learning · Computer Science 2020-05-19 Ravi Raju , Mikko Lipasti

Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the…

Cryptography and Security · Computer Science 2024-03-26 Arijit Ghosh Chowdhury , Md Mofijul Islam , Vaibhav Kumar , Faysal Hossain Shezan , Vaibhav Kumar , Vinija Jain , Aman Chadha

Neural models enjoy widespread use across a variety of tasks and have grown to become crucial components of many industrial systems. Despite their effectiveness and extensive popularity, they are not without their exploitable flaws.…

Sound · Computer Science 2019-02-26 Krishan Rajaratnam , Jugal Kalita

Detecting hallucinations in large language models (LLMs) remains a fundamental challenge for their trustworthy deployment. Going beyond basic uncertainty-driven hallucination detection frameworks, we propose a simple yet powerful method…

Artificial Intelligence · Computer Science 2025-10-10 Rui Wang , Zeming Wei , Guanzhang Yue , Meng Sun
‹ Prev 1 8 9 10 Next ›