Cover Image

Rethinking Fraud Safety Evaluation: Multi-Round Attacks Reveal Safety-Utility Tradeoffs in Graph-Context LLM Defenders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Laura, Ryan, Reza, Li, Qian, Ferdosian, Nasim
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection
by: Jiang, Laura, et al.
Published: (2025)

Smart Surveillance: Identifying IoT Device Behaviours using ML-Powered Traffic Analysis
by: Ryan, Reza, et al.
Published: (2025)

GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
by: He, Sinan, et al.
Published: (2025)

The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents
by: Sah, Tanmay, et al.
Published: (2026)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
by: Xu, Zhangchen, et al.
Published: (2024)

PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
by: Shen, Guobin, et al.
Published: (2025)

detectGNN: Harnessing Graph Neural Networks for Enhanced Fraud Detection in Credit Card Transactions
by: Sultana, Irin, et al.
Published: (2025)

SPARD: Defending Harmful Fine-Tuning Attack via Safety Projection with Relevance-Diversity Data Selection
by: Chen, Shuhao, et al.
Published: (2026)

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning
by: Xue, Zhiyu, et al.
Published: (2024)

Conditional Cube Attack on Round-Reduced ASCON
by: Li, Zheng, et al.
Published: (2025)

LLM-Safety Evaluations Lack Robustness
by: Beyer, Tim, et al.
Published: (2025)

Defensive Refusal Bias: How Safety Alignment Fails Cyber Defenders
by: Campbell, David, et al.
Published: (2026)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
by: An, Li, et al.
Published: (2025)

NeST: Neuron Selective Tuning for LLM Safety
by: Behrouzi, Sasha, et al.
Published: (2026)

Model Poisoning Attacks to Federated Learning via Multi-Round Consistency
by: Xie, Yueqi, et al.
Published: (2024)

Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries
by: Hung, Ki Sen, et al.
Published: (2026)

Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis
by: Xu, Zhenhao, et al.
Published: (2026)

Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
by: Xiong, Yuan, et al.
Published: (2025)

Web Fraud Attacks Against LLM-Driven Multi-Agent Systems
by: Kong, Dezhang, et al.
Published: (2025)

Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
by: Zhang, Xiaozhe, et al.
Published: (2026)

Fuzzerfly Effect: Hardware Fuzzing for Memory Safety
by: Rostami, Mohamadreza, et al.
Published: (2024)

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
by: Xu, Naen, et al.
Published: (2026)

Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool
by: Li, Jiangtong, et al.
Published: (2024)

LLM-Assisted Authentication and Fraud Detection
by: Chan, Emunah S-S., et al.
Published: (2026)

A Game-Theoretic Approach to Privacy-Utility Tradeoff in Sharing Genomic Summary Statistics
by: Zhang, Tao, et al.
Published: (2024)

Unveiling the Threat of Fraud Gangs to Graph Neural Networks: Multi-Target Graph Injection Attacks Against GNN-Based Fraud Detectors
by: Choi, Jinhyeok, et al.
Published: (2024)

PromoGuardian: Detecting Promotion Abuse Fraud with Multi-Relation Fused Graph Neural Networks
by: Li, Shaofei, et al.
Published: (2025)

HarmChip: Evaluating Hardware Security Centric LLM Safety via Jailbreak Benchmarking
by: Wang, Zeng, et al.
Published: (2026)

Usability as a Weapon: Attacking the Safety of LLM-Based Code Generation via Usability Requirements
by: Li, Yue, et al.
Published: (2026)

SAGE: A Generic Framework for LLM Safety Evaluation
by: Jindal, Madhur, et al.
Published: (2025)

Quantifying LLM Safety Degradation Under Repeated Attacks Using Survival Analysis
by: Topol, Zvi
Published: (2026)

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems
by: Zhang, Lingxi, et al.
Published: (2026)

Foe for Fraud: Transferable Adversarial Attacks in Credit Card Fraud Detection
by: Fok, Jan Lum, et al.
Published: (2025)

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
by: Weng, Shihao, et al.
Published: (2026)

Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
by: Chanda, Dibaloke, et al.
Published: (2023)

Benchmarking Fraud Detectors on Private Graph Data
by: Goldberg, Alexander, et al.
Published: (2025)

GSPR: Aligning LLM Safeguards as Generalizable Safety Policy Reasoners
by: Li, Haoran, et al.
Published: (2025)

SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data
by: Zhou, Yan, et al.
Published: (2025)

Optimizing Privacy and Utility Tradeoffs for Group Interests Through Harmonization
by: Mandal, Bishwas, et al.
Published: (2024)

TWGuard: A Case Study of LLM Safety Guardrails for Localized Linguistic Contexts
by: Chu, Hua-Rong, et al.
Published: (2026)