Pith. sign in

REVIEW 11 cited by

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2403.04783 v2 pith:IE3I4HUQ submitted 2024-03-02 cs.LG cs.CLcs.CR

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks

Yifan Zeng , Yiran Wu , Xiao Zhang , Huazheng Wang , Qingyun Wu This is my paper
classification cs.LG cs.CLcs.CR
keywords autodefensedefensejailbreakattacksdifferentllmsmodelsagents
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Despite extensive pre-training in moral alignment to prevent generating harmful information, large language models (LLMs) remain vulnerable to jailbreak attacks. In this paper, we propose AutoDefense, a multi-agent defense framework that filters harmful responses from LLMs. With the response-filtering mechanism, our framework is robust against different jailbreak attack prompts, and can be used to defend different victim models. AutoDefense assigns different roles to LLM agents and employs them to complete the defense task collaboratively. The division in tasks enhances the overall instruction-following of LLMs and enables the integration of other defense components as tools. With AutoDefense, small open-source LMs can serve as agents and defend larger models against jailbreak attacks. Our experiments show that AutoDefense can effectively defense against different jailbreak attacks, while maintaining the performance at normal user request. For example, we reduce the attack success rate on GPT-3.5 from 55.74% to 7.95% using LLaMA-2-13b with a 3-agent system. Our code and data are publicly available at https://github.com/XHMY/AutoDefense.

discussion (0)

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

Forward citations

Cited by 11 Pith papers

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

  1. ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation

    cs.CR 2025-07 unverdicted novelty 8.0

    ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.

  2. Mitigating Taint-Style Vulnerabilities in MCP Servers via Security-Aware Tool Descriptions

    cs.CR 2026-07 conditional novelty 6.0

    SPELLSMITH mitigates taint-style vulnerabilities in MCP servers by augmenting tool descriptions with security constraints and adding LLM self-reflection before tool invocation, reducing attack success rates to near zero.

  3. From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection

    cs.CV 2025-10 conditional novelty 6.0

    A multi-agent forensic system integrates multiple evidence sources and debate to detect AI-generated images, reporting 97.05% accuracy on a 6,000-image benchmark while outperforming traditional classifiers.

  4. Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem

    cs.CR 2025-06 unverdicted novelty 6.0

    Formalizes the jailbreak oracle problem for LLMs and introduces Boa, a two-phase breadth-first then depth-first search system to solve it efficiently.

  5. Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

    cs.CR 2026-07 unverdicted novelty 5.0

    Cognitive Firewall applies four gates (intent, zero-trust context, consistency, output risk) via an oversight model to cut jailbreak success to 2% or below on most tested sets while keeping over-refusal at 8%.

  6. Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models

    cs.CR 2026-05 unverdicted novelty 5.0

    Behavioral geometry of model populations enables high-accuracy jailbreak susceptibility prediction and defense transfer with 98% fewer evaluations.

  7. SoK: Robustness in Large Language Models against Jailbreak Attacks

    cs.CR 2026-05 accept novelty 5.0

    The paper taxonomizes jailbreak attacks and defenses for LLMs, introduces the Security Cube multi-dimensional evaluation framework, benchmarks 13 attacks and 5 defenses, and identifies open challenges in LLM robustness.

  8. GAMMAF: A Common Framework for Graph-Based Anomaly Monitoring Benchmarking in LLM Multi-Agent Systems

    cs.CR 2026-04 unverdicted novelty 5.0

    GAMMAF provides a benchmarking platform with data generation and defense evaluation pipelines for graph-based anomaly detection in LLM multi-agent systems, demonstrating improved integrity and lower operational costs ...

  9. Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts

    cs.CR 2025-10 unverdicted novelty 4.0

    Sentra-Guard reports 99.96% detection of adversarial LLM prompts with AUC 1.00 and ASR of 0.004% using a hybrid SBERT-FAISS and transformer classifier architecture with multilingual translation and human feedback.

  10. Jailbreak Attacks and Defenses Against Large Language Models: A Survey

    cs.CR 2024-07 accept novelty 4.0

    A survey that creates taxonomies for jailbreak attacks and defenses on LLMs, subdivides them into sub-classes, and compares evaluation approaches.

  11. 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.