Cover Image

Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Nawal, Aditya, Baser, Manit, Gurusamy, Mohan
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
by: Sinha, Yash, et al.
Published: (2025)

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement
by: Shetty, Anudeex, et al.
Published: (2026)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
by: Wang, Kun, et al.
Published: (2026)

How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
by: Zhou, Zhenhong, et al.
Published: (2024)

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
by: Li, Xueyi, et al.
Published: (2026)

What Matters For Safety Alignment?
by: Li, Xing, et al.
Published: (2026)

Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
by: Wang, Yanbo, et al.
Published: (2026)

AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models
by: Zhang, Jinchuan, et al.
Published: (2025)

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
by: Tong, Terry, et al.
Published: (2025)

Mapping the Exploitation Surface: A 10,000-Trial Taxonomy of What Makes LLM Agents Exploit Vulnerabilities
by: Mouzouni, Charafeddine
Published: (2026)

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
by: Wang, Xilong, et al.
Published: (2026)

Improving LLM Reasoning for Vulnerability Detection via Group Relative Policy Optimization
by: Simoni, Marco, et al.
Published: (2025)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
by: Li, Hao, et al.
Published: (2026)

SAGE-RT: Synthetic Alignment data Generation for Safety Evaluation and Red Teaming
by: Kumar, Anurakt, et al.
Published: (2024)

From Threat to Tool: Leveraging Refusal-Aware Injection Attacks for Safety Alignment
by: Chae, Kyubyung, et al.
Published: (2025)

WAInjectBench: Benchmarking Prompt Injection Detections for Web Agents
by: Liu, Yinuo, et al.
Published: (2025)

Safety Alignment Should Be Made More Than Just A Few Attention Heads
by: Huang, Chao, et al.
Published: (2025)

GFCL: A GRU-based Federated Continual Learning Framework against Data Poisoning Attacks in IoV
by: Talpur, Anum, et al.
Published: (2022)

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection
by: Sahoo, Devanshu, et al.
Published: (2025)

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

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
by: Li, Tianhao, et al.
Published: (2024)

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

Safety Alignment Can Be Not Superficial With Explicit Safety Signals
by: Li, Jianwei, et al.
Published: (2025)

RuleForge: Automated Generation and Validation for Web Vulnerability Detection at Scale
by: Garg, Ayush, et al.
Published: (2026)

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

Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw
by: Wang, Zijun, et al.
Published: (2026)

DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
by: Zhang, Junbo, et al.
Published: (2026)

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

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

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

Lifelong Safety Alignment for Language Models
by: Wang, Haoyu, et al.
Published: (2025)

Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs
by: Xing, Wenpeng, et al.
Published: (2025)

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

Exploring Backdoor Vulnerabilities of Chat Models
by: Hao, Yunzhuo, et al.
Published: (2024)

Large Language Model Sentinel: LLM Agent for Adversarial Purification
by: Lin, Guang, et al.
Published: (2024)

How Well Can LLM Agents Simulate End-User Security and Privacy Attitudes and Behaviors?
by: Li, Yuxuan, et al.
Published: (2026)

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities
by: Khattar, Vanshaj, et al.
Published: (2026)

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
by: Wang, Kun, et al.
Published: (2025)

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
by: Lee, Hyomin, et al.
Published: (2026)

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