mlsanityData to 7 Oct 2026

SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks

arXiv 2601.19174 ↗First posted 27 Jan 2026cs.CR cs.AIcited by 1

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that fail on semantically meaningful attacks or use static LLM-based detectors that struggle to adapt as attack strategies evolve. We introduce SHIELD, a multi-agent, auto-healing defense framework centered on a three-stage Defense Agent that integrates semantic similarity retrieval, pattern matching, and LLM-based reasoning. Two auxiliary agents, a Knowledge Updating Agent and a Prompt Optimization Agent, form a closed self-healing loop, when an attack bypasses detection, the system updates an evolving knowledgebase, and refines defense instructions. Extensive experiments show that SHIELD consistently outperforms perplexity-based and standalone LLM defenses, achieving high F1 scores across both non-semantic and semantic sponge attacks, demonstrating the effectiveness of agentic self-healing against evolving resource-exhaustion threats.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 23 of its 32 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

23 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks2 Mar

Other references · 22

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  3. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,018
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  5. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  6. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  7. 2023Large Language Models as Optimizerscited by 830
  8. 2020Aligning AI With Shared Human Valuescited by 706
  9. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 630
  10. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  11. 2023Detecting Language Model Attacks with Perplexitycited by 411
  12. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
10 more
  1. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  2. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 226
  3. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  4. 2023Defending Against Alignment-Breaking Attacks via Robustly Aligned LLMcited by 173
  5. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  6. 2024SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Mannercited by 57
  7. 2024Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settingscited by 33
  8. 2024Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM Compressioncited by 32
  9. 2024An Engorgio Prompt Makes Large Language Model Babble oncited by 30
  10. 2025Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmarkcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challengescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
  2. 2026PropGuard: Safeguarding LLM-MAS via Propagation-Aware Exploration and Remediation
  3. 2026Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
  4. 2026Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
  5. 2026AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization
  6. 2026CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?
  7. 2026Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
  8. 2026From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails