Pith. sign in

REVIEW 17 cited by

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.09523 v1 pith:CEIL7I3G submitted 2024-11-14 cs.AI

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

classification cs.AI
keywords agentsrisksthreatsllm-basedllmsresearchanalyzedifferent
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

With the continuous development of large language models (LLMs), transformer-based models have made groundbreaking advances in numerous natural language processing (NLP) tasks, leading to the emergence of a series of agents that use LLMs as their control hub. While LLMs have achieved success in various tasks, they face numerous security and privacy threats, which become even more severe in the agent scenarios. To enhance the reliability of LLM-based applications, a range of research has emerged to assess and mitigate these risks from different perspectives. To help researchers gain a comprehensive understanding of various risks, this survey collects and analyzes the different threats faced by these agents. To address the challenges posed by previous taxonomies in handling cross-module and cross-stage threats, we propose a novel taxonomy framework based on the sources and impacts. Additionally, we identify six key features of LLM-based agents, based on which we summarize the current research progress and analyze their limitations. Subsequently, we select four representative agents as case studies to analyze the risks they may face in practical use. Finally, based on the aforementioned analyses, we propose future research directions from the perspectives of data, methodology, and policy, respectively.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis

    cs.CR 2026-04 accept novelty 8.0

    Agent Skills has structural security weaknesses from missing data-instruction boundaries, single-approval persistent trust, and absent marketplace reviews that require fundamental redesign.

  2. Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

    cs.CR 2025-03 unverdicted novelty 7.0

    MCP lifecycle is defined with four phases and 16 activities; a threat taxonomy of 16 scenarios is constructed, validated via case studies, and paired with phase-specific safeguards.

  3. Large Language Models Hack Rewards, and Society

    cs.LG 2026-06 unverdicted novelty 6.0

    LLMs discover regulatory loopholes in simulated societal environments through reward hacking during RL training.

  4. Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.

  5. Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem

    cs.SE 2026-05 unverdicted novelty 6.0

    MCP-BiFlow detects 93.8% of known bidirectional data-flow vulnerabilities in MCP servers and identifies 118 confirmed issues across 87 real-world servers from a scan of 15,452 repositories.

  6. Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

    cs.CR 2026-03 unverdicted novelty 6.0

    The survey organizes over 400 papers on embodied AI safety into a multi-level taxonomy and flags overlooked issues such as fragile multimodal fusion and unstable planning under jailbreaks.

  7. Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

    cs.CR 2026-03 accept novelty 6.0

    A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.

  8. LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems

    cs.CR 2025-09 conditional novelty 6.0

    A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.

  9. BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks

    cs.AI 2025-08 unverdicted novelty 6.0

    BlindGuard introduces an unsupervised hierarchical agent encoder plus corruption-guided contrastive detector that identifies malicious agents in LLM-based multi-agent systems without any attack labels or prior knowled...

  10. Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

    cs.CR 2026-06 unverdicted novelty 5.0

    A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.

  11. Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering

    cs.SE 2026-06 unverdicted novelty 5.0

    Interviews with 20 practitioners show MCP supports cross-system collaboration and task decoupling in LLM workflows but is limited by ecosystem fragmentation, coordination issues, and state management problems.

  12. Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment

    cs.AI 2026-05 unverdicted novelty 5.0

    A three-layer probabilistic assume-guarantee architecture is structurally required for safe LLM agent deployment.

  13. Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks

    cs.CR 2026-06 unverdicted novelty 4.0

    ParDef defends DNNs against sparse, continuous, and structured parameter attacks via keyed reparameterization, error-correcting quantization, and robust inference, with evaluations on CIFAR and Tiny-ImageNet showing r...

  14. On the Privacy of LLMs: An Ablation Study

    cs.CR 2026-05 unverdicted novelty 4.0

    Privacy attacks on LLMs show strong signals for membership inference and backdoors but weaker performance for attribute inference and data extraction, with risks highly dependent on system configuration.

  15. LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling

    physics.comp-ph 2026-04 unverdicted novelty 4.0

    LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.

  16. Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

    cs.CR 2026-06 unverdicted novelty 3.0

    A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.

  17. Large Language Model Agent: A Survey on Methodology, Applications and Challenges

    cs.CL 2025-03 accept novelty 3.0

    A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.