Copertina

MergeGuard: Efficient Thwarting of Trojan Attacks in Machine Learning Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Shabgahi, Soheil Zibakhsh, Jandali, Yaman, Koushanfar, Farinaz
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimizing Privacy-Preserving Primitives to Support LLM-Scale Applications
di: Jandali, Yaman, et al.
Pubblicazione: (2025)

Trojan Cleansing with Neural Collapse
di: Gu, Xihe, et al.
Pubblicazione: (2024)

Props for Machine-Learning Security
di: Juels, Ari, et al.
Pubblicazione: (2024)

Beyond Perplexity: A Lightweight Benchmark for Knowledge Retention in Supervised Fine-Tuning
di: Shabgahi, Soheil Zibakhsh, et al.
Pubblicazione: (2026)

LayerCollapse: Adaptive compression of neural networks
di: Shabgahi, Soheil Zibakhsh, et al.
Pubblicazione: (2023)

ForTIFAI: Fending Off Recursive Training Induced Failure for AI Model Collapse
di: Shabgahi, Soheil Zibakhsh, et al.
Pubblicazione: (2025)

Magmaw: Modality-Agnostic Adversarial Attacks on Machine Learning-Based Wireless Communication Systems
di: Chang, Jung-Woo, et al.
Pubblicazione: (2023)

AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
di: Zhang, Ruisi, et al.
Pubblicazione: (2025)

ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
di: Sheybani, Nojan, et al.
Pubblicazione: (2025)

LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
di: Spracklen, Joseph, et al.
Pubblicazione: (2026)

Double-Dip: Thwarting Label-Only Membership Inference Attacks with Transfer Learning and Randomization
di: Rajabi, Arezoo, et al.
Pubblicazione: (2024)

Watermarking Large Language Models and the Generated Content: Opportunities and Challenges
di: Zhang, Ruisi, et al.
Pubblicazione: (2024)

EmMark: Robust Watermarks for IP Protection of Embedded Quantized Large Language Models
di: Zhang, Ruisi, et al.
Pubblicazione: (2024)

SkillTrojan: Backdoor Attacks on Skill-Based Agent Systems
di: Feng, Yunhao, et al.
Pubblicazione: (2026)

TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning
di: Liu, Yupei, et al.
Pubblicazione: (2025)

HOACS: Homomorphic Obfuscation Assisted Concealing of Secrets to Thwart Trojan Attacks in COTS Processor
di: Hossain, Tanvir, et al.
Pubblicazione: (2024)

Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
di: Wang, Hongtao, et al.
Pubblicazione: (2026)

Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging
di: Latibari, Banafsheh Saber, et al.
Pubblicazione: (2025)

Trojans in Artificial Intelligence (TrojAI) Final Report
di: Reese, Kristopher W., et al.
Pubblicazione: (2026)

TrojanWhisper: Evaluating Pre-trained LLMs to Detect and Localize Hardware Trojans
di: Faruque, Md Omar, et al.
Pubblicazione: (2024)

ICtoken: An NFT for Hardware IP Protection
di: Balla, Shashank, et al.
Pubblicazione: (2024)

Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
di: Saha, Shoumik, et al.
Pubblicazione: (2026)

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks
di: Zhang, Xu, et al.
Pubblicazione: (2025)

Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
di: Guan, Faqian, et al.
Pubblicazione: (2024)

Defending Against Beta Poisoning Attacks in Machine Learning Models
di: Gulciftci, Nilufer, et al.
Pubblicazione: (2025)

LiveTune: Dynamic Parameter Tuning for Feedback-Driven Optimization
di: Shabgahi, Soheil Zibakhsh, et al.
Pubblicazione: (2023)

Quantum Properties Trojans (QuPTs) for Attacking Quantum Neural Networks
di: Bhowmik, Sounak, et al.
Pubblicazione: (2025)

X-Guard: Multilingual Guard Agent for Content Moderation
di: Upadhayay, Bibek, et al.
Pubblicazione: (2025)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
di: Li, Siyuan, et al.
Pubblicazione: (2026)

CoT-Guard: Small Models for Strong Monitoring
di: Diwan, Nirav, et al.
Pubblicazione: (2026)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
di: Wang, Haoran, et al.
Pubblicazione: (2023)

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
di: Das, Debeshee, et al.
Pubblicazione: (2026)

Adversarial Machine Learning: Attacks, Defenses, and Open Challenges
di: Jha, Pranav K
Pubblicazione: (2025)

REMARK-LLM: A Robust and Efficient Watermarking Framework for Generative Large Language Models
di: Zhang, Ruisi, et al.
Pubblicazione: (2023)

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models
di: Liu, Xuxu, et al.
Pubblicazione: (2025)

Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
di: Li, Qinfeng, et al.
Pubblicazione: (2025)

Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
di: Wulnye, Fortunatus Aabangbio, et al.
Pubblicazione: (2026)

Zero-Knowledge Proof Frameworks: A Systematic Survey
di: Sheybani, Nojan, et al.
Pubblicazione: (2025)

LoBAM: LoRA-Based Backdoor Attack on Model Merging
di: Yin, Ming, et al.
Pubblicazione: (2024)

SWIFT: Semantic Watermarking for Image Forgery Thwarting
di: Evennou, Gautier, et al.
Pubblicazione: (2024)