Pith. sign in

REVIEW 7 cited by

Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

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 2505.04806 v2 pith:AZK5LCCM submitted 2025-05-07 cs.CR cs.CL

classification cs.CRcs.CL
keywords llmsadversarialinjectionjailbreakpromptstrategiessystematicalignment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation of jailbreak strategies against various state-of-the-art LLMs. We categorize over 1,400 adversarial prompts, analyze their success against GPT-4, Claude 2, Mistral 7B, and Vicuna, and examine their generalizability and construction logic. We further propose layered mitigation strategies and recommend a hybrid red-teaming and sandboxing approach for robust LLM security.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents

    cs.LG 2026-05 unverdicted novelty 8.0 of 10

    OTora provides the first unified framework for reasoning-level denial-of-service attacks on LLM agents, achieving up to 10x more reasoning tokens and order-of-magnitude latency increases while preserving task accuracy...

  2. kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

    cs.LG 2026-07 unverdicted novelty 6.0 of 10

    Multi-layer Fisher-weighted kNN over frozen-LLM activations, fused with embedding kNN, yields competitive F1 guardrails from a 50-example bank with no fine-tuning and sub-10-second domain adaptation.

  3. ANNIE: Be Careful of Your Robots

    cs.AI 2025-09 conditional novelty 6.0 of 10

    The authors build a safety-centered benchmark and attack method that induces vision-language-action robot policies to violate ISO-based safety rules in a majority of tested episodes.

  4. Mass-Scale Analysis of In-the-Wild Conversations Reveals Complexity Bounds on LLM Jailbreaking

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Across 2M+ in-the-wild LLM conversations, jailbreak attempts show no higher complexity than normal chats, and assistant toxicity has declined over time, suggesting bounded attack sophistication.

  5. Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks

    cs.CR 2026-04 conditional novelty 5.0 of 10

    Refusal-aligned LLMs leak system instructions under encoding/serialization prompts at high rates, and one-shot CoT instruction reshaping substantially reduces that leakage without retraining.

  6. A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents

    cs.AI 2025-06 conditional novelty 4.0 of 10

    The paper surveys security risks of LLM agents, organizes them into a five-level autonomy taxonomy, and proposes an untested CMDP-based architecture called R2A2.

  7. Exposing Hidden Backdoors in NFT Smart Contracts: A Static Security Analysis of Rug Pull Patterns

    cs.CR 2025-06 reject novelty 3.0 of 10

    A static analysis of nearly 50,000 Ethereum NFT contracts finds that 22.6% contain multiple rug-pull-related code patterns, though the study does not validate these flags against confirmed scams.

Pith tools