Cover Image

Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Zihao, Tong, Yu, Wu, Weibin, Wang, Jingyi, Chen, Lifeng, Zhao, Zhe, Wei, Jiajia, Qiao, Yitong, Zheng, Zibin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

An Empirical Study on the Security Vulnerabilities of GPTs
by: Wu, Tong, et al.
Published: (2025)

GPU in the Blind Spot: Overlooked Security Risks in Transportation
by: Puspa, Sefatun-Noor, et al.
Published: (2025)

Devilray: A Systematic Adversarial Model Revealing Blind Spots in Fake Base Station Detection
by: Oh, Taekkyung, et al.
Published: (2026)

VisuoAlign: Safety Alignment of LVLMs with Multimodal Tree Search
by: Li, MingSheng, et al.
Published: (2025)

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
by: Ding, Xuwei, et al.
Published: (2026)

MANA: Towards Efficient Mobile Ad Detection via Multimodal Agentic UI Navigation
by: Zhao, Yizhe, et al.
Published: (2026)

Control at Stake: Evaluating the Security Landscape of LLM-Driven Email Agents
by: Wu, Jiangrong, et al.
Published: (2025)

Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents
by: Xu, Zhen, et al.
Published: (2026)

ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
by: Zheng, Yusheng, et al.
Published: (2026)

A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
by: Zhao, Puning, et al.
Published: (2024)

MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs
by: Wu, Zhenpeng, et al.
Published: (2024)

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents
by: Wu, Jiangrong, et al.
Published: (2026)

SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
by: Wu, Jiangrong, et al.
Published: (2026)

GoAT-X: A Graph of Auditing Thoughts for Securing Token Transactions in Cross-Chain Contracts
by: Feng, Zijun, et al.
Published: (2026)

FedCAPrivacy: Privacy-Preserving Heterogeneous Federated Learning with Anonymous Adaptive Clustering
by: Wei, Yunan, et al.
Published: (2025)

Robust Anti-Backdoor Instruction Tuning in LVLMs
by: Xun, Yuan, et al.
Published: (2025)

DCS Chain: A Flexible Private Blockchain System
by: Zheng, Jianwu, et al.
Published: (2024)

BrokerChain: A Blockchain Sharding Protocol by Exploiting Broker Accounts
by: Huang, Huawei, et al.
Published: (2024)

Detecting Avalanche Effect in Adversarial Settings: Spotting the Encryption Loops in Ransomware
by: Luo, Nanqing, et al.
Published: (2026)

A Fast-Detection and Fault-Correction Algorithm against Persistent Fault Attack
by: Cheng, Yukun, et al.
Published: (2021)

Towards Strengthening Deep Learning-based Side Channel Attacks with Mixup
by: Luo, Zhimin, et al.
Published: (2021)

BLACKOUT: Data-Oblivious Computation with Blinded Capabilities
by: ElAtali, Hossam, et al.
Published: (2025)

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing
by: Yin, Jinhua, et al.
Published: (2025)

Unity is Strength: Enhancing Precision in Reentrancy Vulnerability Detection of Smart Contract Analysis Tools
by: Wang, Zexu, et al.
Published: (2024)

Blockchain-empowered Federated Learning: Benefits, Challenges, and Solutions
by: Cai, Zeju, et al.
Published: (2024)

Uncover the Premeditated Attacks: Detecting Exploitable Reentrancy Vulnerabilities by Identifying Attacker Contracts
by: Yang, Shuo, et al.
Published: (2024)

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
by: Zhang, Shenyi, et al.
Published: (2025)

How Blind and Low-Vision Users Manage Their Passwords
by: Ponticello, Alexander, et al.
Published: (2025)

Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron
by: Zhao, Gejian, et al.
Published: (2025)

METANOIA: A Lifelong Intrusion Detection and Investigation System for Mitigating Concept Drift
by: Ying, Jie, et al.
Published: (2024)

DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection
by: Ren, Junyu, et al.
Published: (2026)

StruPhantom: Evolutionary Injection Attacks on Black-Box Tabular Agents Powered by Large Language Models
by: Feng, Yang, et al.
Published: (2025)

Your Code Secret Belongs to Me: Neural Code Completion Tools Can Memorize Hard-Coded Credentials
by: Huang, Yizhan, et al.
Published: (2023)

BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks
by: Zheng, Meixi, et al.
Published: (2023)

Linking Souls to Humans: Blockchain Accounts with Credible Anonymity for Web 3.0 Decentralized Identity
by: Wang, Taotao, et al.
Published: (2023)

BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption
by: Gronberg, Evan, et al.
Published: (2025)

ReThink: Reveal the Threat of Electromagnetic Interference on Power Inverters
by: Yang, Fengchen, et al.
Published: (2024)

SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security
by: Zhao, Wei, et al.
Published: (2025)

PortGPT: Towards Automated Backporting Using Large Language Models
by: Li, Zhaoyang, et al.
Published: (2025)

Resource Allocation and Secure Wireless Communication in the Large Model-based Mobile Edge Computing System
by: Wang, Zefan, et al.
Published: (2024)