Cover Image

The Surface You Test Is Not the Surface That Breaks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Arman, Shifat E, Sakib, Syed Nazmus, Haque, Nafiul, Amin, Shahrear Bin
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PATHWAYS: Evaluating Investigation and Context Discovery in AI Web Agents
by: Arman, Shifat E., et al.
Published: (2026)

PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
by: Haque, Nafiul, et al.
Published: (2026)

PlantVillageVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science
by: Sakib, Syed Nazmus, et al.
Published: (2025)

Thinking Like a Botanist: Challenging Multimodal Language Models with Intent-Driven Chain-of-Inquiry
by: Sakib, Syed Nazmus, et al.
Published: (2026)

We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
by: Spracklen, Joseph, et al.
Published: (2024)

VocalBridge: Latent Diffusion-Bridge Purification for Defeating Perturbation-Based Voiceprint Defenses
by: Abbasihafshejani, Maryam, et al.
Published: (2026)

Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In
by: Nakash, Itay, et al.
Published: (2024)

Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
by: Rafid, Mohammad Ishzaz Asif, et al.
Published: (2025)

Defenses Against Prompt Attacks Learn Surface Heuristics
by: Li, Shawn, et al.
Published: (2026)

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
by: Arzanipour, Atousa, et al.
Published: (2025)

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
by: Van hamme, Tim, et al.
Published: (2026)

Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization
by: Verma, Ishaan, et al.
Published: (2025)

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
by: Chen, Yanzuo, et al.
Published: (2023)

CompressionAttack: Exploiting Prompt Compression as a New Attack Surface in LLM-Powered Agents
by: Liu, Zesen, et al.
Published: (2025)

Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation
by: Liu, Zehao, et al.
Published: (2025)

Serverless AI Security: Attack Surface Analysis and Runtime Protection Mechanisms for FaaS-Based Machine Learning
by: Pathade, Chetan, et al.
Published: (2026)

The System Prompt Is the Attack Surface: How LLM Agent Configuration Shapes Security and Creates Exploitable Vulnerabilities
by: Litvak, Ron
Published: (2026)

Delayed Backdoor Attacks: Exploring the Temporal Dimension as a New Attack Surface in Pre-Trained Models
by: Ding, Zikang, et al.
Published: (2026)

Explainable Adversarial Learning Framework on Physical Layer Secret Keys Combating Malicious Reconfigurable Intelligent Surface
by: Wei, Zhuangkun, et al.
Published: (2024)

Attention Is Where You Attack
by: Srivastava, Aviral, et al.
Published: (2026)

Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors
by: Borjigin, Ailiya, et al.
Published: (2026)

Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
by: Chen, Sizhe, et al.
Published: (2025)

You Can Backdoor Personalized Federated Learning
by: Ye, Tiandi, et al.
Published: (2023)

Jailbreaking is (Mostly) Simpler Than You Think
by: Russinovich, Mark, et al.
Published: (2025)

Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
by: Ng, Jonathan Hong Jin, et al.
Published: (2026)

The End of Trust: How Agentic AI Breaks Security Assumptions
by: Zafar, Osama, et al.
Published: (2026)

I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors
by: Lin, Zijin, et al.
Published: (2024)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
by: Evtimov, Ivan, et al.
Published: (2025)

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
by: Zhang, Chuhan, et al.
Published: (2025)

Breaking Guardrails, Facing Walls: Insights on Adversarial AI for Defenders & Researchers
by: Bertollo, Giacomo, et al.
Published: (2025)

Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch
by: Zhao, Qichen, et al.
Published: (2026)

Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
by: Zhang, Gehao, et al.
Published: (2025)

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation
by: Zhu, Wentian, et al.
Published: (2025)

Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code
by: Kim, Jungin, et al.
Published: (2025)

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
by: Wang, Zhibo, et al.
Published: (2024)

What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else?
by: Ma, Boyang, et al.
Published: (2026)

Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
by: Saha, Shoumik, et al.
Published: (2025)

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
by: Wang, Hao, et al.
Published: (2026)

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
by: Ding, Ruomeng, et al.
Published: (2026)

Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions
by: Guo, Xuyang, et al.
Published: (2025)