Cover Image

Shadows in the Code: Exploring the Risks and Defenses of LLM-based Multi-Agent Software Development Systems

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Xiaoqing, Huang, Keman, Liang, Bin, Li, Hongyu, Du, Xiaoyong
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
by: Xu, Naen, et al.
Published: (2026)

Contextualized Privacy Defense for LLM Agents
by: Wen, Yule, et al.
Published: (2026)

MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
by: Wang, Yuhui, et al.
Published: (2026)

Practically implementing an LLM-supported collaborative vulnerability remediation process: a team-based approach
by: Wang, Xiaoqing, et al.
Published: (2024)

Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
by: Luo, Zhifan, et al.
Published: (2025)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
by: An, Hengyu, et al.
Published: (2025)

Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity games
by: Yan, Yikuan, et al.
Published: (2024)

IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems
by: Wang, Liwen, et al.
Published: (2025)

Searching for Privacy Risks in LLM Agents via Simulation
by: Zhang, Yanzhe, et al.
Published: (2025)

Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
by: Zhang, Hanrong, et al.
Published: (2024)

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning
by: Du, Xiaohu, et al.
Published: (2024)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
by: Qu, Yubin, et al.
Published: (2026)

DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation
by: Jiang, Bo
Published: (2026)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
by: Fujinuma, Yoshinari, et al.
Published: (2026)

Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection
by: Song, Chengyu, et al.
Published: (2024)

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
by: Dingeto, Hiskias, et al.
Published: (2026)

Exploring Backdoor Attack and Defense for LLM-empowered Recommendations
by: Ning, Liangbo, et al.
Published: (2025)

Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs
by: Yan, Dong, et al.
Published: (2026)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation
by: Long, Zhuohang, et al.
Published: (2025)

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration
by: Patil, Vaidehi, et al.
Published: (2025)

Exploring and Developing a Pre-Model Safeguard with Draft Models
by: Cai, Hongyu, et al.
Published: (2026)

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

SOK: Exploring Hallucinations and Security Risks in AI-Assisted Software Development with Insights for LLM Deployment
by: Haque, Ariful, et al.
Published: (2025)

Test-Time Immunization: A Universal Defense Framework Against Jailbreaks for (Multimodal) Large Language Models
by: Yu, Yongcan, et al.
Published: (2025)

PsySafe: A Comprehensive Framework for Psychological-based Attack, Defense, and Evaluation of Multi-agent System Safety
by: Zhang, Zaibin, et al.
Published: (2024)

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
by: Dong, Jianshuo, et al.
Published: (2025)

Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
by: Liu, Jinbo, et al.
Published: (2025)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
by: Yang, Wenkai, et al.
Published: (2024)

HauntAttack: When Attack Follows Reasoning as a Shadow
by: Ma, Jingyuan, et al.
Published: (2025)

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
by: Shen, Xinjie, et al.
Published: (2026)

Taxonomy, Evaluation and Exploitation of IPI-Centric LLM Agent Defense Frameworks
by: Ji, Zimo, et al.
Published: (2025)

Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
by: Yu, Zhenxiong, et al.
Published: (2026)

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
by: Zhao, Andrew, et al.
Published: (2025)

SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
by: Qu, Yubin, et al.
Published: (2026)

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents
by: Das, Saswat, et al.
Published: (2025)

NeuroFilter: Privacy Guardrails for Conversational LLM Agents
by: Das, Saswat, et al.
Published: (2026)

MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue
by: Wang, Fengxiang, et al.
Published: (2024)

SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
by: Gu, Chenxi, et al.
Published: (2026)

A Survey on Agentic Security: Applications, Threats and Defenses
by: Shahriar, Asif, et al.
Published: (2025)