Cover Image

DeepSeek on a Trip: Inducing Targeted Visual Hallucinations via Representation Vulnerabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Islam, Chashi Mahiul, Chacko, Samuel Jacob, Horne, Preston, Liu, Xiuwen
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers
by: Islam, Chashi Mahiul, et al.
Published: (2025)

Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning
by: Islam, Chashi Mahiul, et al.
Published: (2025)

Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems
by: Islam, Chashi Mahiul, et al.
Published: (2024)

Are Vision Transformer Representations Semantically Meaningful? A Case Study in Medical Imaging
by: Shams, Montasir, et al.
Published: (2025)

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
by: Chacko, Samuel Jacob, et al.
Published: (2026)

Adversarial Attacks on Large Language Models Using Regularized Relaxation
by: Chacko, Samuel Jacob, et al.
Published: (2024)

DeepSeek-OCR 2: Visual Causal Flow
by: Wei, Haoran, et al.
Published: (2026)

DeepSeek-OCR: Contexts Optical Compression
by: Wei, Haoran, et al.
Published: (2025)

Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR
by: Liang, Yunhao, et al.
Published: (2026)

Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models
by: Islam, Chashi Mahiul, et al.
Published: (2026)

DeepSeek-Inspired Exploration of RL-based LLMs and Synergy with Wireless Networks: A Survey
by: Qiao, Yu, et al.
Published: (2025)

Can LLMs Assist Computer Education? an Empirical Case Study of DeepSeek
by: Xiao, Dongfu, et al.
Published: (2025)

Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition
by: Tang, Haocheng, et al.
Published: (2026)

Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek
by: Li, Xueyang, et al.
Published: (2025)

MHA2MLA-VLM: Enabling DeepSeek's Economical Multi-Head Latent Attention across Vision-Language Models
by: Fan, Xiaoran, et al.
Published: (2026)

Transformation of Biological Networks into Images via Semantic Cartography for Visual Interpretation and Scalable Deep Analysis
by: Mostafa, Sakib, et al.
Published: (2025)

Suppressing VLM Hallucinations with Spectral Representation Filtering
by: Ali, Ameen, et al.
Published: (2025)

From ChatGPT to DeepSeek AI: A Comprehensive Analysis of Evolution, Deviation, and Future Implications in AI-Language Models
by: Singh, Simrandeep, et al.
Published: (2025)

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
by: Wu, Zhiyu, et al.
Published: (2024)

Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations
by: Jiang, Nick, et al.
Published: (2024)

Understanding Multimodal Hallucination with Parameter-Free Representation Alignment
by: Wang, Yueqian, et al.
Published: (2024)

Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
by: Dang, Tiantian, et al.
Published: (2026)

Comparative Analysis of OpenAI GPT-4o and DeepSeek R1 for Scientific Text Categorization Using Prompt Engineering
by: Maiti, Aniruddha, et al.
Published: (2025)

Hessian Surgery: Class-Targeted Post-Hoc Rebalancing via Hessian Spike Perturbation
by: Vigna, Hugo, et al.
Published: (2026)

Tab2Visual: Overcoming Limited Data in Tabular Data Classification Using Deep Learning with Visual Representations
by: Mamdouh, Ahmed, et al.
Published: (2025)

Visual Hallucinations of Multi-modal Large Language Models
by: Huang, Wen, et al.
Published: (2024)

Mode Seeking meets Mean Seeking for Fast Long Video Generation
by: Cai, Shengqu, et al.
Published: (2026)

Improving Deep Representation Learning via Auxiliary Learnable Target Coding
by: Liu, Kangjun, et al.
Published: (2023)

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
by: Kalibhat, Neha, et al.
Published: (2024)

Revealing Vulnerabilities in Stable Diffusion via Targeted Attacks
by: Zhang, Chenyu, et al.
Published: (2024)

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
by: Li, Zhuowei, et al.
Published: (2025)

A Scoping Review of Deep Learning for Urban Visual Pollution and Proposal of a Real-Time Monitoring Framework with a Visual Pollution Index
by: Rahman, Mohammad Masudur, et al.
Published: (2026)

Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery
by: Ma, Boyi, et al.
Published: (2025)

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models
by: Liu, Zhongye, et al.
Published: (2024)

SEMIR: Semantic Minor-Induced Representation Learning on Graphs for Visual Segmentation
by: Miller, Luke James, et al.
Published: (2026)

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs
by: Kolli, Govinda, et al.
Published: (2026)

ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
by: Park, Yeji, et al.
Published: (2024)

GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
by: Parast, Aryan Yazdan, et al.
Published: (2025)

Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models
by: Yan, YangTian, et al.
Published: (2025)

Intriguing Equivalence Structures of the Embedding Space of Vision Transformers
by: Salman, Shaeke, et al.
Published: (2024)