Cover Image

Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Banerjee, Sarbartha, Sahu, Prateek, Vahldiek-Oberwagner, Anjo, Vicarte, Jose Sanchez, Tiwari, Mohit
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

SoK: A Systems Perspective on Compound AI Threats and Countermeasures
by: Banerjee, Sarbartha, et al.
Published: (2024)

It's a Feature, Not a Bug: Secure and Auditable State Rollback for Confidential Cloud Applications
by: Burke, Quinn, et al.
Published: (2025)

ConfusedPilot: Confused Deputy Risks in RAG-based LLMs
by: RoyChowdhury, Ayush, et al.
Published: (2024)

Making 'syscall' a Privilege not a Right
by: Yang, Fangfei, et al.
Published: (2024)

Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloud
by: Chrapek, Marcin, et al.
Published: (2024)

Obsidian: Cooperative State-Space Exploration for Performant Inference on Secure ML Accelerators
by: Banerjee, Sarbartha, et al.
Published: (2024)

Threat Modeling for AI: The Case for an Asset-Centric Approach
by: Vicarte, Jose Sanchez, et al.
Published: (2025)

Blockchain Amplification Attack
by: Tsuchiya, Taro, et al.
Published: (2024)

Deserialization Gadget Chains are not a Pathological Problem in Android:an In-Depth Study of Java Gadget Chains in AOSP
by: Kreyssig, Bruno, et al.
Published: (2025)

One Key Good, L Keys Better: List Decoding Meets Quantum Privacy Amplification
by: Kulkarni, Prateek P.
Published: (2026)

ThreatPilot: Attack-Driven Threat Intelligence Extraction
by: Xu, Ming, et al.
Published: (2024)

Structural Representations for Cross-Attack Generalization in AI Agent Threat Detection
by: Iyer, Vignesh
Published: (2026)

ADMIn: Attacks on Dataset, Model and Input. A Threat Model for AI Based Software
by: Kumar, Vimal, et al.
Published: (2024)

When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
by: Sun, Zehan, et al.
Published: (2026)

Exploiting AI for Attacks: On the Interplay between Adversarial AI and Offensive AI
by: Schröer, Saskia Laura, et al.
Published: (2025)

Energy-Latency Attacks: A New Adversarial Threat to Deep Learning
by: Meftah, Hanene F. Z. Brachemi, et al.
Published: (2025)

GHunter: Universal Prototype Pollution Gadgets in JavaScript Runtimes
by: Cornelissen, Eric, et al.
Published: (2024)

Software-Hardware Binding for Protection of Sensitive Data in Embedded Software
by: Fischer, Bernhard, et al.
Published: (2026)

RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework
by: Ikbarieh, Seif, et al.
Published: (2025)

Hardware-Efficient Compound IC Protection with Lightweight Cryptography
by: Aksoy, Levent, et al.
Published: (2026)

Cyber Threat Hunting: Non-Parametric Mining of Attack Patterns from Cyber Threat Intelligence for Precise Threats Attribution
by: Kanwal, Rimsha, et al.
Published: (2025)

Security Analysis of WiFi-based Sensing Systems: Threats from Perturbation Attacks
by: Cao, Hangcheng, et al.
Published: (2024)

ATAG: AI-Agent Application Threat Assessment with Attack Graphs
by: Gandhi, Parth Atulbhai, et al.
Published: (2025)

Detecting Adversarial Data via Provable Adversarial Noise Amplification
by: Mumcu, Furkan, et al.
Published: (2026)

"Are Adversarial Phishing Webpages a Threat in Reality?" Understanding the Users' Perception of Adversarial Webpages
by: Yuan, Ying, et al.
Published: (2024)

Fresh Masking Makes NTT Pipelines Composable: Machine-Checked Proofs for Arithmetic Masking in PQC Hardware
by: Iskander, Ray, et al.
Published: (2026)

Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
by: Zou, Quanchen, et al.
Published: (2026)

Mitigating Error Amplification in Fast Adversarial Training
by: Zhao, Mengnan, et al.
Published: (2026)

Steering in the Shadows: Causal Amplification for Activation Space Attacks in Large Language Models
by: Xu, Zhiyuan, et al.
Published: (2025)

Teapot: Efficiently Uncovering Spectre Gadgets in COTS Binaries
by: Lin, Fangzheng, et al.
Published: (2024)

Composable Attestation: A Generalized Framework for Continuous and Incremental Trust in AI-Driven Distributed Systems
by: Sun, Sheng, et al.
Published: (2026)

Bribe & Fork: Cheap Bribing Attacks via Forking Threat
by: Avarikioti, Zeta, et al.
Published: (2024)

Adversarial Threats in Quantum Machine Learning: A Survey of Attacks and Defenses
by: Ghosh, Archisman, et al.
Published: (2025)

A Novel Classification of Attacks on Blockchain Layers: Vulnerabilities, Attacks, Mitigations, and Research Directions
by: Dwivedi, Kaustubh, et al.
Published: (2024)

Autonomous Threat Hunting: A Future Paradigm for AI-Driven Threat Intelligence
by: Sindiramutty, Siva Raja
Published: (2023)

Secure Software/Hardware Hybrid In-Field Testing for System-on-Chip
by: Mulhem, Saleh, et al.
Published: (2024)

Logical Maneuvers: Detecting and Mitigating Adversarial Hardware Faults in Space
by: Dana, Fatemeh Khojasteh, et al.
Published: (2025)

Design for Assurance: Employing Functional Verification Tools for Thwarting Hardware Trojan Threat in 3PIPs
by: Hu, Wei, et al.
Published: (2023)

Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
by: Xue, Jing, et al.
Published: (2025)

Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems
by: Ward, Chris M., et al.
Published: (2025)